Deep Learning

Publications and preprints

Preprints and reports

1. Combettes, C., Spiegel, C., and Pokutta, S. (2020). Projection-Free Adaptive Gradients for Large-Scale Optimization. [arXiv] [summary] [code]
   [BibTeX]

   @misc{2020_CombettesSpiegelPokutta_Projectionfreeadaptivegradients,
     archiveprefix = {arXiv},
     eprint = {2009.14114},
     arxiv = {arXiv:2009.14114},
     primaryclass = {math.OC},
     author = {Combettes, Cyrille and Spiegel, Christoph and Pokutta, Sebastian},
     title = {Projection-Free Adaptive Gradients for Large-Scale Optimization},
     code = {https://github.com/ZIB-IOL/StochasticFrankWolfe},
     summary = {https://pokutta.com/blog/research/2020/10/21/adasfw.html},
     date = {2020-09-29}
   }

2. Pokutta, S., Spiegel, C., and Zimmer, M. (2020). Deep Neural Network Training with Frank-Wolfe. [arXiv] [summary] [code]
   [BibTeX]

   @misc{2020_PokuttaSpiegelZimmer_Frankwolfeneuralnetworks,
     archiveprefix = {arXiv},
     eprint = {2010.07243},
     arxiv = {arXiv:2010.07243},
     primaryclass = {cs.LG},
     author = {Pokutta, Sebastian and Spiegel, Christoph and Zimmer, Max},
     title = {Deep Neural Network Training with Frank-Wolfe},
     code = {https://github.com/ZIB-IOL/StochasticFrankWolfe},
     summary = {https://pokutta.com/blog/research/2020/11/11/NNFW.html},
     date = {2020-10-14}
   }

3. Zimmer, M., Andoni, M., Spiegel, C., and Pokutta, S. (2023). PERP: Rethinking the Prune-Retrain Paradigm in the Era of LLMs. [arXiv] [code]
   [BibTeX]

   @misc{2023_ZimmerAndoniSpiegelPokutta_PerpPruneRetrain,
     archiveprefix = {arXiv},
     eprint = {2312.15230},
     arxiv = {arXiv:2312.15230},
     primaryclass = {cs.LG},
     author = {Zimmer, Max and Andoni, Megi and Spiegel, Christoph and Pokutta, Sebastian},
     title = {PERP: Rethinking the Prune-Retrain Paradigm in the Era of LLMs},
     code = {https://github.com/ZIB-IOL/PERP},
     date = {2023-12-23}
   }

4. Goerigk, M., Hartisch, M., Merten, S., and Sharma, K. (2024). Feature-Based Interpretable Surrogates for Optimization. [arXiv]
   [BibTeX]

   @misc{2024_GoerigkHartischMertenSharma_Featureinterpretableoptimization,
     archiveprefix = {arXiv},
     eprint = {2409.01869},
     arxiv = {arXiv:2409.01869},
     primaryclass = {math.OC},
     author = {Goerigk, Marc and Hartisch, Michael and Merten, Sebastian and Sharma, Kartikey},
     title = {Feature-Based Interpretable Surrogates for Optimization},
     date = {2024-09-03}
   }

5. Mundinger, K., Zimmer, M., and Pokutta, S. (2024). Neural Parameter Regression for Explicit Representations of PDE Solution Operators. [arXiv]
   [BibTeX]

   @misc{2024_MundingerZimmerPokutta_Neuralparameterregression,
     archiveprefix = {arXiv},
     eprint = {2403.12764},
     arxiv = {arXiv:2403.12764},
     primaryclass = {cs.LG},
     author = {Mundinger, Konrad and Zimmer, Max and Pokutta, Sebastian},
     title = {Neural Parameter Regression for Explicit Representations of PDE Solution Operators},
     date = {2024-03-19}
   }

6. Yoda, K., Kawamoto, K., and Kera, H. (2025). Learning Moderately Input-Sensitive Functions: A Case Study in QR Code Decoding. [arXiv]
   [BibTeX]

   @misc{2025_KazukiKazuhikoKera_Qrcodedecoding_2506-20305,
     archiveprefix = {arXiv},
     eprint = {2506.20305},
     arxiv = {arXiv:2506.20305},
     primaryclass = {cs.LG},
     author = {Yoda, Kazuki and Kawamoto, Kazuhiko and Kera, Hiroshi},
     title = {Learning Moderately Input-Sensitive Functions: A Case Study in QR Code Decoding},
     date = {2025-06-25}
   }

7. Kera, H., and Kehrein, A. (2025). Gradient-Weighted, Data-Driven Normalization for Approximate Border Bases – Concept and Computation. [arXiv]
   [BibTeX]

   @misc{2025_KeraAchim_Gradientweightednormalization_2506-09529,
     archiveprefix = {arXiv},
     eprint = {2506.09529},
     arxiv = {arXiv:2506.09529},
     primaryclass = {cs.SC},
     author = {Kera, Hiroshi and Kehrein, Achim},
     title = {Gradient-Weighted, Data-Driven Normalization for Approximate Border Bases -- Concept and Computation},
     date = {2025-06-11}
   }

8. Kera, H., Arakawa, S., and Sato, Y. (2025). CALT: A Library for Computer Algebra with Transformer. [arXiv]
   [BibTeX]

   @misc{2025_KeraShunYuta_Calttransformer_2506-08600,
     archiveprefix = {arXiv},
     eprint = {2506.08600},
     arxiv = {arXiv:2506.08600},
     primaryclass = {cs.LG},
     author = {Kera, Hiroshi and Arakawa, Shun and Sato, Yuta},
     title = {CALT: A Library for Computer Algebra with Transformer},
     date = {2025-06-10}
   }

9. Koshizuka, T., and Sato, I. (2025). Understanding Generalization in Physics Informed Models through Affine Variety Dimensions. [arXiv]
   [BibTeX]

   @misc{2025_KoshizukaIssei_Generalizationaffinevariety_2501-18879,
     archiveprefix = {arXiv},
     eprint = {2501.18879},
     arxiv = {arXiv:2501.18879},
     primaryclass = {cs.LG},
     author = {Koshizuka, Takeshi and Sato, Issei},
     title = {Understanding Generalization in Physics Informed Models through Affine Variety Dimensions},
     date = {2025-01-31}
   }

10. Roux, C., Zimmer, M., d’Aspremont, A., and Pokutta, S. (2025). Don’t Be Greedy, Just Relax! Pruning LLMs via Frank-Wolfe. [arXiv]
    [BibTeX]

    @misc{2025_RouxZimmerDaspremontPokutta_Pruningfrankwolfe_2510-13713,
      archiveprefix = {arXiv},
      eprint = {2510.13713},
      arxiv = {arXiv:2510.13713},
      primaryclass = {cs.LG},
      author = {Roux, Christophe and Zimmer, Max and d'Aspremont, Alexandre and Pokutta, Sebastian},
      title = {Don't Be Greedy, Just Relax! Pruning LLMs via Frank-Wolfe},
      date = {2025-10-15}
    }

11. Sadiku, S., Chitranshi, K., Kera, H., and Pokutta, S. (2025). Training on Plausible Counterfactuals Removes Spurious Correlations. [arXiv]
    [BibTeX]

    @misc{2025_SadikuChitranshiKeraPokutta_Plausiblecounterfactuals,
      archiveprefix = {arXiv},
      eprint = {2505.16583},
      arxiv = {arXiv:2505.16583},
      primaryclass = {cs.LG},
      author = {Sadiku, Shpresim and Chitranshi, Kartikeya and Kera, Hiroshi and Pokutta, Sebastian},
      title = {Training on Plausible Counterfactuals Removes Spurious Correlations},
      date = {2025-05-22}
    }

12. Kumano, S., Kera, H., and Yamasaki, T. (2025). Adversarially Pretrained Transformers May Be Universally Robust In-Context Learners. [arXiv]
    [BibTeX]

    @misc{2025_SoichiroKeraToshihiko_Adversarialtransformers,
      archiveprefix = {arXiv},
      eprint = {2505.14042},
      arxiv = {arXiv:2505.14042},
      primaryclass = {cs.LG},
      author = {Kumano, Soichiro and Kera, Hiroshi and Yamasaki, Toshihiko},
      title = {Adversarially Pretrained Transformers May Be Universally Robust In-Context Learners},
      date = {2025-05-20}
    }

13. Sato, Y., Kawamoto, K., and Kera, H. (2025). Discovering Learning-Friendly Generation Orders for Sequential Computation. [arXiv]
    [BibTeX]

    @misc{2025_YutaKazuhikoKera_Chainthoughtordering_2506-23875,
      archiveprefix = {arXiv},
      eprint = {2506.23875},
      arxiv = {arXiv:2506.23875},
      primaryclass = {cs.LG},
      author = {Sato, Yuta and Kawamoto, Kazuhiko and Kera, Hiroshi},
      title = {Discovering Learning-Friendly Generation Orders for Sequential Computation},
      date = {2025-06-30}
    }

14. Zimmer, M., Roux, C., Wagner, M., Hendrych, D., and Pokutta, S. (2025). SparseSwaps: Tractable LLM Pruning Mask Refinement at Scale. [arXiv]
    [BibTeX]

    @misc{2025_ZimmerEtAl_Sparseswapspruning_2512-10922,
      archiveprefix = {arXiv},
      eprint = {2512.10922},
      arxiv = {arXiv:2512.10922},
      primaryclass = {cs.LG},
      author = {Zimmer, Max and Roux, Christophe and Wagner, Moritz and Hendrych, Deborah and Pokutta, Sebastian},
      title = {SparseSwaps: Tractable LLM Pruning Mask Refinement at Scale},
      date = {2025-12-11}
    }

15. Batzner, J., Nelaturu, H., Stachura, D., Kornilova, A., Crall, J., Cerruti, T., Long, Y., Mai, Y., Ahuja, S., Yehudai, A., Šuppa, M., Lalor, J. P., Olowe, O., Ganhotra, J., Hu, B. H., Habba, E., Bean, A. M., Liu, C., Land, S., … Choshen, L. (2026). Every Eval Ever: A Unifying Schema and Community Repository for AI Evaluation Results. [arXiv]
    [BibTeX]

    @misc{2026_BatznerEtAl_EvalSchemaRepository_2606-14516,
      archiveprefix = {arXiv},
      eprint = {2606.14516},
      arxiv = {arXiv:2606.14516},
      primaryclass = {cs.AI},
      author = {Batzner, Jan and Nelaturu, Harsha and Stachura, Damian and Kornilova, Anastassia and Crall, Jon and Cerruti, Tommaso and Long, Yanan and Mai, Yifan and Ahuja, Sanchit and Yehudai, Asaf and Šuppa, Marek and Lalor, John P. and Olowe, Oluwagbemike and Ganhotra, Jatin and Hu, Brian H. and Habba, Eliya and Bean, Andrew M. and Liu, Chang and Land, Sander and Dillmann, Steven and Garikaparthi, Aniketh and Bandel, Elron and Imai, Saki and Edgell, James and Kennedy, Wm. Matthew and Chim, Jenny and Meusling, Patrick and Kaeberlein, Asteria and Chundi, Venkata Ramachandra Karthik and Patwardhan, Manasi and Ku, Martin and Meek, Austin and Knauer, Leon and Wingenroth, Brian and Yadav, Srishti and Gohar, Usman and Friedrich, Felix and Lin, Michelle and Mickel, Jennifer and Cohan, Arman and Biderman, Stella and Solaiman, Irene and Talat, Zeerak and Reuel, Anka and Akhtar, Mubashara and Kasneci, Gjergji and Ghosh, Avijit and Choshen, Leshem},
      title = {Every Eval Ever: A Unifying Schema and Community Repository for AI Evaluation Results},
      date = {2026-06-12}
    }

16. Pauls, J., Schrödter, K., Ligensa, S., Schwartz, M., Turan, B., Zimmer, M., Saatchi, S., Pokutta, S., Ciais, P., and Gieseke, F. (2026). ECHOSAT: Estimating Canopy Height Over Space And Time. [arXiv]
    [BibTeX]

    @misc{2026_JanEtAl_EchosatCanopyheight_2602-21421,
      archiveprefix = {arXiv},
      eprint = {2602.21421},
      arxiv = {arXiv:2602.21421},
      primaryclass = {cs.CV},
      author = {Pauls, Jan and Schrödter, Karsten and Ligensa, Sven and Schwartz, Martin and Turan, Berkant and Zimmer, Max and Saatchi, Sassan and Pokutta, Sebastian and Ciais, Philippe and Gieseke, Fabian},
      title = {ECHOSAT: Estimating Canopy Height Over Space And Time},
      date = {2026-02-24}
    }

17. Leins, N., Pelleriti, N., Gonnermann-Müller, J., and Pokutta, S. (2026). When Does LLM Orchestration Pay Off? A Controlled Evaluation of Accuracy, Cost, and Task Difficulty. [arXiv]
    [BibTeX]

    @misc{2026_LeinsPelleritiGonnermannmuellerPokutta_Llmorchestration_2608-00685,
      archiveprefix = {arXiv},
      eprint = {2608.00685},
      arxiv = {arXiv:2608.00685},
      primaryclass = {cs.AI},
      author = {Leins, Nicolas and Pelleriti, Nico and Gonnermann-Müller, Jana and Pokutta, Sebastian},
      title = {When Does LLM Orchestration Pay Off? A Controlled Evaluation of Accuracy, Cost, and Task Difficulty},
      date = {2026-08-01}
    }

18. Pelleriti, N., Nelaturu, S. H., Zhou, Z., Li, Z., Zimmer, M., Han, B., and Pokutta, S. (2026). What Do Evolutionary Coding Agents Evolve? [arXiv]
    [BibTeX]

    @misc{2026_PelleritiEtAl_Evotrace_2605-20086,
      archiveprefix = {arXiv},
      eprint = {2605.20086},
      arxiv = {arXiv:2605.20086},
      primaryclass = {cs.NE},
      author = {Pelleriti, Nico and Nelaturu, Sree Harsha and Zhou, Zhanke and Li, Zongze and Zimmer, Max and Han, Bo and Pokutta, Sebastian},
      title = {What Do Evolutionary Coding Agents Evolve?},
      date = {2026-05-19}
    }

19. Pelleriti, N., Shiran, M., Martínez-Rubio, D., Zimmer, M., and Pokutta, S. (2026). Optimal Gradient-Norm Minimization in Non-Euclidean Hölder-Smooth Convex Optimization. [arXiv]
    [BibTeX]

    @misc{2026_PelleritiEtAl_GradientNormNonEuclidean_2609-01122,
      archiveprefix = {arXiv},
      eprint = {2609.01122},
      arxiv = {arXiv:2609.01122},
      primaryclass = {math.OC},
      author = {Pelleriti, Nico and Shiran, Maryam and Martínez-Rubio, David and Zimmer, Max and Pokutta, Sebastian},
      title = {Optimal Gradient-Norm Minimization in Non-Euclidean Hölder-Smooth Convex Optimization},
      date = {2026-09-01}
    }

20. Schiekiera, L., Zimmer, M., Roux, C., Arnold, M., Pokutta, S., and Günther, F. (2026). LinearPFN: Amortized Variable Selection for Linear Models with Interactions. [arXiv]
    [BibTeX]

    @misc{2026_SchiekieraEtAl_LinearPFNVariableSelection_2610-06580,
      archiveprefix = {arXiv},
      eprint = {2610.06580},
      arxiv = {arXiv:2610.06580},
      primaryclass = {cs.LG},
      author = {Schiekiera, Louis and Zimmer, Max and Roux, Christophe and Arnold, Manuel and Pokutta, Sebastian and Günther, Fritz},
      title = {LinearPFN: Amortized Variable Selection for Linear Models with Interactions},
      date = {2026-10-05}
    }

21. Urbano, A., Romero, D. W., Zimmer, M., and Pokutta, S. (2026). Neural Field Tokenizations with Hierarchy and Spatial Locality Priors. [arXiv]
    [BibTeX]

    @misc{2026_UrbanoRomeroZimmerPokutta_Neuralfieldtokenization_2606-08204,
      archiveprefix = {arXiv},
      eprint = {2606.08204},
      arxiv = {arXiv:2606.08204},
      primaryclass = {cs.LG},
      author = {Urbano, Alonso and Romero, David W. and Zimmer, Max and Pokutta, Sebastian},
      title = {Neural Field Tokenizations with Hierarchy and Spatial Locality Priors},
      date = {2026-06-06}
    }

22. Wagner, M., Roux, C., Zimmer, M., and Pokutta, S. (2026). The KV-Surgeon: Compensation-Aware Offline KV-Cache Compaction. [arXiv]
    [BibTeX]

    @misc{2026_WagnerRouxZimmerPokutta_KVCacheCompaction_2610-25933,
      archiveprefix = {arXiv},
      eprint = {2610.25933},
      arxiv = {arXiv:2610.25933},
      primaryclass = {cs.LG},
      author = {Wagner, Moritz and Roux, Christophe and Zimmer, Max and Pokutta, Sebastian},
      title = {The KV-Surgeon: Compensation-Aware Offline KV-Cache Compaction},
      date = {2026-10-19}
    }

23. Zhou, Z., Li, Z., Huang, W., Li, X., Cao, C., Feng, X., Lu, X., Hu, J., Xie, Y., Pelleriti, N., Liu, S., Lu, M., Zimmer, M., Miranda, B., Yao, J., Liu, B., Koyejo, S., Pokutta, S., and Han, B. (2026). AlphaDiana: A Measurement System for Agents in Verifiable Reasoning Tasks. [arXiv]
    [BibTeX]

    @misc{2026_ZhouEtAl_AlphaDianaVerifiableReasoning_2610-20675,
      archiveprefix = {arXiv},
      eprint = {2610.20675},
      arxiv = {arXiv:2610.20675},
      primaryclass = {cs.AI},
      author = {Zhou, Zhanke and Li, Zongze and Huang, Weikai and Li, Xuan and Cao, Chentao and Feng, Xiao and Lu, Xiangyu and Hu, Jinbo and Xie, Yi and Pelleriti, Nico and Liu, Shiyang and Lu, Menghan and Zimmer, Max and Miranda, Brando and Yao, Jiangchao and Liu, Bo and Koyejo, Sanmi and Pokutta, Sebastian and Han, Bo},
      title = {AlphaDiana: A Measurement System for Agents in Verifiable Reasoning Tasks},
      date = {2026-10-14}
    }

24. Zimmer, M., Pelleriti, N., Roux, C., and Pokutta, S. (2026). The Agentic Researcher: A Practical Guide to AI-Assisted Research in Mathematics and Machine Learning. [arXiv]
    [BibTeX]

    @misc{2026_ZimmerPelleritiRouxPokutta_Airesearchframework_2603-15914,
      archiveprefix = {arXiv},
      eprint = {2603.15914},
      arxiv = {arXiv:2603.15914},
      primaryclass = {cs.LG},
      author = {Zimmer, Max and Pelleriti, Nico and Roux, Christophe and Pokutta, Sebastian},
      title = {The Agentic Researcher: A Practical Guide to AI-Assisted Research in Mathematics and Machine Learning},
      date = {2026-03-16}
    }

25. Geiselmann, Z., Joswig, M., Kastner, L., Mundinger, K., Pokutta, S., Spiegel, C., Wack, M., and Zimmer, M. (2026). Limits of combinatorial patchworking. [arXiv]
    [BibTeX]

    @misc{2026_ZoeEtAl_Patchworkedcurves_2602-06888,
      archiveprefix = {arXiv},
      eprint = {2602.06888},
      arxiv = {arXiv:2602.06888},
      primaryclass = {math.AG},
      author = {Geiselmann, Zoe and Joswig, Michael and Kastner, Lars and Mundinger, Konrad and Pokutta, Sebastian and Spiegel, Christoph and Wack, Marcel and Zimmer, Max},
      title = {Limits of combinatorial patchworking},
      date = {2026-02-06}
    }

Conference contributions

1. Wagner, M., Roux, C., Zimmer, M., and Pokutta, S. A Free Lunch in LLM Compression: Revisiting Retraining after Pruning. Advances in Neural Information Processing Systems, 39. To appear. Associated with NeurIPS 2026. [arXiv]
   [BibTeX]

   @inproceedings{2025_WagnerRouxZimmerPokutta_Llmpruningretraining_2510-14444,
     booktitle = {Advances in Neural Information Processing Systems},
     series = {Advances in Neural Information Processing Systems},
     volume = {39},
     publisher = {Curran Associates},
     note = {To appear},
     archiveprefix = {arXiv},
     eprint = {2510.14444},
     arxiv = {arXiv:2510.14444},
     primaryclass = {cs.LG},
     author = {Wagner, Moritz and Roux, Christophe and Zimmer, Max and Pokutta, Sebastian},
     title = {A Free Lunch in LLM Compression: Revisiting Retraining after Pruning}
   }

2. Halbey, J., Roux, C., and Pokutta, S. Curvature-Dependent Lower Bounds for Frank-Wolfe. Advances in Neural Information Processing Systems, 39. To appear. Associated with NeurIPS 2026. [arXiv]
   [BibTeX]

   @inproceedings{2026_HalbeyRouxPokutta_Curvaturelowerbounds_2605-10595,
     booktitle = {Advances in Neural Information Processing Systems},
     series = {Advances in Neural Information Processing Systems},
     volume = {39},
     publisher = {Curran Associates},
     note = {To appear},
     archiveprefix = {arXiv},
     eprint = {2605.10595},
     arxiv = {arXiv:2605.10595},
     primaryclass = {math.OC},
     author = {Halbey, Jannis and Roux, Christophe and Pokutta, Sebastian},
     title = {Curvature-Dependent Lower Bounds for Frank-Wolfe}
   }

3. Koshizuka, T., Blessing, D., Zimmer, M., Pokutta, S., and Richter, L. A Trust Region Approach for Learning Schrödinger Bridges. Advances in Neural Information Processing Systems, 39. To appear. Associated with NeurIPS 2026.
   [BibTeX]

   @inproceedings{2026_KoshizukaEtAl_TrustregionSchrodingerbridges,
     booktitle = {Advances in Neural Information Processing Systems},
     series = {Advances in Neural Information Processing Systems},
     volume = {39},
     publisher = {Curran Associates},
     note = {To appear},
     author = {Koshizuka, Takeshi and Blessing, Denis and Zimmer, Max and Pokutta, Sebastian and Richter, Lorenz},
     title = {A Trust Region Approach for Learning Schrödinger Bridges}
   }

4. Geiselmann, Z., Joswig, M., Kastner, L., Mundinger, K., Pokutta, S., Spiegel, C., Wack, M., and Zimmer, M. (2027). Fast Isotopy Computation for T-Curves. Mathematical Software – ICMS 2026, 16677. To appear. Associated with ICMS 2026. [URL] [arXiv]
   [BibTeX]

   @inproceedings{2026_ZoeEtAl_Isotopytcurves_2604-09221,
     year = {2027},
     booktitle = {Mathematical Software – ICMS 2026},
     series = {Lecture Notes in Computer Science},
     volume = {16677},
     publisher = {Springer Science+Business Media},
     note = {To appear},
     url = {https://icms-conference.org/2026/papers/paper32/main.pdf},
     archiveprefix = {arXiv},
     eprint = {2604.09221},
     arxiv = {arXiv:2604.09221},
     primaryclass = {math.AG},
     author = {Geiselmann, Zoe and Joswig, Michael and Kastner, Lars and Mundinger, Konrad and Pokutta, Sebastian and Spiegel, Christoph and Wack, Marcel and Zimmer, Max},
     title = {Fast Isotopy Computation for T-Curves}
   }

5. Turan, B., Asadulla, S., Steinmann, D., Kersting, K., Stammer, W., and Pokutta, S. (2026). Neural Concept Verifier: Scaling Prover-Verifier Games via Concept Encodings. Proceedings of the 43rd International Conference on Machine Learning, 306. Associated with ICML 2026. [arXiv]
   [BibTeX]

   @inproceedings{2025_TuranEtAl_Neuralconceptverifier_2507-07532,
     year = {2026},
     booktitle = {Proceedings of the 43rd International Conference on Machine Learning},
     series = {Proceedings of Machine Learning Research},
     volume = {306},
     month = jul,
     archiveprefix = {arXiv},
     eprint = {2507.07532},
     arxiv = {arXiv:2507.07532},
     primaryclass = {cs.LG},
     author = {Turan, Berkant and Asadulla, Suhrab and Steinmann, David and Kersting, Kristian and Stammer, Wolfgang and Pokutta, Sebastian},
     title = {Neural Concept Verifier: Scaling Prover-Verifier Games via Concept Encodings}
   }

6. Muhtar, D., Song, X., Pokutta, S., Zimmer, M., Pelleriti, N., Hofmann, T., and Liu, S. (2026). When Does Sparsity Mitigate the Curse of Depth in LLMs. Proceedings of the 43rd International Conference on Machine Learning, 306. Associated with ICML 2026. [arXiv]
   [BibTeX]

   @inproceedings{2026_DilxatEtAl_Sparsitydepthllms_2603-15389,
     year = {2026},
     booktitle = {Proceedings of the 43rd International Conference on Machine Learning},
     series = {Proceedings of Machine Learning Research},
     volume = {306},
     month = jul,
     archiveprefix = {arXiv},
     eprint = {2603.15389},
     arxiv = {arXiv:2603.15389},
     primaryclass = {cs.CL},
     author = {Muhtar, Dilxat and Song, Xinyuan and Pokutta, Sebastian and Zimmer, Max and Pelleriti, Nico and Hofmann, Thomas and Liu, Shiwei},
     title = {When Does Sparsity Mitigate the Curse of Depth in LLMs}
   }

7. Halbey, J., Deza, D., Zimmer, M., Roux, C., Stellato, B., and Pokutta, S. (2026). Lower Bounds for Frank-Wolfe on Strongly Convex Sets. Proceedings of the 43rd International Conference on Machine Learning, 306. Associated with ICML 2026. [arXiv]
   [BibTeX]

   @inproceedings{2026_HalbeyEtAl_Lowerboundsfrankwolfe_2602-04378,
     year = {2026},
     booktitle = {Proceedings of the 43rd International Conference on Machine Learning},
     series = {Proceedings of Machine Learning Research},
     volume = {306},
     month = jul,
     archiveprefix = {arXiv},
     eprint = {2602.04378},
     arxiv = {arXiv:2602.04378},
     primaryclass = {math.OC},
     author = {Halbey, Jannis and Deza, Daniel and Zimmer, Max and Roux, Christophe and Stellato, Bartolomeo and Pokutta, Sebastian},
     title = {Lower Bounds for Frank-Wolfe on Strongly Convex Sets}
   }

8. Schiekiera, L., Zimmer, M., Roux, C., Pokutta, S., and Günther, F. (2026). From Associations to Activations: Comparing Behavioral and Hidden-State Semantic Geometry in LLMs. Proceedings of the 43rd International Conference on Machine Learning, 306. Associated with ICML 2026. [arXiv]
   [BibTeX]

   @inproceedings{2026_LouisEtAl_Behavioralgeometry_2602-00628,
     year = {2026},
     booktitle = {Proceedings of the 43rd International Conference on Machine Learning},
     series = {Proceedings of Machine Learning Research},
     volume = {306},
     month = jul,
     archiveprefix = {arXiv},
     eprint = {2602.00628},
     arxiv = {arXiv:2602.00628},
     primaryclass = {cs.LG},
     author = {Schiekiera, Louis and Zimmer, Max and Roux, Christophe and Pokutta, Sebastian and Günther, Fritz},
     title = {From Associations to Activations: Comparing Behavioral and Hidden-State Semantic Geometry in LLMs}
   }

9. Urbano, A., Romero, D. W., Zimmer, M., and Pokutta, S. (2026, January). RECON: Robust symmetry discovery via Explicit Canonical Orientation Normalization. International Conference on Learning Representations 2026. Associated with ICLR 2026. [arXiv]
   [BibTeX]

   @inproceedings{2025_UrbanoWZimmerPokutta_Reconsymmetrydiscovery,
     year = {2026},
     booktitle = {International Conference on Learning Representations 2026},
     publisher = {ICLR (OpenReview)},
     month = jan,
     archiveprefix = {arXiv},
     eprint = {2505.13289},
     arxiv = {arXiv:2505.13289},
     primaryclass = {cs.LG},
     author = {Urbano, Alonso and Romero, David W. and Zimmer, Max and Pokutta, Sebastian},
     title = {RECON: Robust symmetry discovery via Explicit Canonical Orientation Normalization}
   }

10. Pelleriti, N., Spiegel, C., Liu, S., Martínez-Rubio, D., Zimmer, M., and Pokutta, S. (2026). Neural Sum-of-Squares: Certifying the Nonnegativity of Polynomials with Transformers. International Conference on Learning Representations 2026. Associated with ICLR 2026. [URL] [arXiv]
    [BibTeX]

    @inproceedings{2025_PelleritiEtAl_Neuralsos_2510-13444,
      year = {2026},
      booktitle = {International Conference on Learning Representations 2026},
      publisher = {ICLR (OpenReview)},
      url = {https://proceedings.iclr.cc/paper_files/paper/2026/hash/1cfb3b066461f1c542be5242a622ce4b-Abstract-Conference.html},
      archiveprefix = {arXiv},
      eprint = {2510.13444},
      arxiv = {arXiv:2510.13444},
      primaryclass = {cs.LG},
      author = {Pelleriti, Nico and Spiegel, Christoph and Liu, Shiwei and Martínez-Rubio, David and Zimmer, Max and Pokutta, Sebastian},
      title = {Neural Sum-of-Squares: Certifying the Nonnegativity of Polynomials with Transformers}
    }

11. Leins, N., Pelleriti, N., Gonnermann-Müller, J., and Pokutta, S. (2026). When Does LLM Orchestration Pay Off? A Controlled Evaluation of Accuracy, Resources, and Task Difficulty. Accepted at NeurIPS 2026 Workshop on Resource-Aware Agentic AI. [arXiv]
    [BibTeX]

    @misc{2026_LeinsPelleritiGonnermannmuellerPokutta_Llmorchestration_2608-00685:1,
      howpublished = {Accepted at NeurIPS 2026 Workshop on Resource-Aware Agentic AI},
      year = {2026},
      archiveprefix = {arXiv},
      eprint = {2608.00685},
      arxiv = {arXiv:2608.00685},
      primaryclass = {cs.AI},
      author = {Leins, Nicolas and Pelleriti, Nico and Gonnermann-Müller, Jana and Pokutta, Sebastian},
      title = {When Does LLM Orchestration Pay Off? A Controlled Evaluation of Accuracy, Resources, and Task Difficulty}
    }

12. Pelleriti, N., Nelaturu, S. H., Zhou, Z., Li, Z., Zimmer, M., Han, B., and Pokutta, S. (2026). What Do Evolutionary Coding Agents Evolve? Accepted at NeurIPS 2026 Workshop on Self-Evolving Diversity-Driven Search for Robust AI Systems. [arXiv]
    [BibTeX]

    @misc{2026_PelleritiEtAl_Evotrace_2605-20086:1,
      howpublished = {Accepted at NeurIPS 2026 Workshop on Self-Evolving Diversity-Driven Search for Robust AI Systems},
      year = {2026},
      archiveprefix = {arXiv},
      eprint = {2605.20086},
      arxiv = {arXiv:2605.20086},
      primaryclass = {cs.NE},
      author = {Pelleriti, Nico and Nelaturu, Sree Harsha and Zhou, Zhanke and Li, Zongze and Zimmer, Max and Han, Bo and Pokutta, Sebastian},
      title = {What Do Evolutionary Coding Agents Evolve?}
    }

13. Pelleriti, N., Kraus, N., May, A., and Pokutta, S. (2026). CryptHarness: A Harness for Agent-Assisted Cryptanalytic Research. Accepted at NeurIPS 2026 Workshop on SaTQuML: Secure and Trustworthy Quantum Machine Learning.
    [BibTeX]

    @misc{2026_PelleritiKrausMayPokutta_CryptHarness,
      howpublished = {Accepted at NeurIPS 2026 Workshop on SaTQuML: Secure and Trustworthy Quantum Machine Learning},
      year = {2026},
      author = {Pelleriti, Nico and Kraus, Nicolai and May, Alexander and Pokutta, Sebastian},
      title = {CryptHarness: A Harness for Agent-Assisted Cryptanalytic Research}
    }

14. Pelleriti, N., Kraus, N., May, A., and Pokutta, S. (2026). CryptHarness: A Harness for Agent-Assisted Cryptanalytic Research. Accepted at Third Workshop on Agents in the Wild: Safety, Security, and Beyond @ NeurIPS 2026.
    [BibTeX]

    @misc{2026_PelleritiKrausMayPokutta_CryptHarness:1,
      howpublished = {Accepted at Third Workshop on Agents in the Wild: Safety, Security, and Beyond @ NeurIPS 2026},
      year = {2026},
      author = {Pelleriti, Nico and Kraus, Nicolai and May, Alexander and Pokutta, Sebastian},
      title = {CryptHarness: A Harness for Agent-Assisted Cryptanalytic Research}
    }

15. Pelleriti, N., Mundinger, K., Zimmer, M., and Pokutta, S. (2026). Zero: A Meta-Agent for Mathematical Research. Accepted at The Sixth Workshop on Mathematical Reasoning and AI @ NeurIPS 2026.
    [BibTeX]

    @misc{2026_PelleritiMundingerZimmerPokutta_Zero,
      howpublished = {Accepted at The Sixth Workshop on Mathematical Reasoning and AI @ NeurIPS 2026},
      year = {2026},
      author = {Pelleriti, Nico and Mundinger, Konrad and Zimmer, Max and Pokutta, Sebastian},
      title = {Zero: A Meta-Agent for Mathematical Research}
    }

16. Pelleriti, N., Mundinger, K., Zimmer, M., and Pokutta, S. (2026). Zero: A Meta-Agent for Mathematical Research. Accepted at First Workshop on Meta Agents: Managing Agents That Manage Agents @ NeurIPS 2026.
    [BibTeX]

    @misc{2026_PelleritiMundingerZimmerPokutta_Zero:1,
      howpublished = {Accepted at First Workshop on Meta Agents: Managing Agents That Manage Agents @ NeurIPS 2026},
      year = {2026},
      author = {Pelleriti, Nico and Mundinger, Konrad and Zimmer, Max and Pokutta, Sebastian},
      title = {Zero: A Meta-Agent for Mathematical Research}
    }

17. Petit-Tichanné, U., Pelleriti, N., Zimmer, M., and Pokutta, S. (2026). Learning the Coefficients of the Standard Volatility Forecaster. Accepted at NeurIPS 2026 Workshop TS-LIMITS: Generalization for Time Series in Tight Settings: Latency, Inference, Memory, PrIvacy and SusTainability.
    [BibTeX]

    @misc{2026_PetitTichannePelleritiZimmerPokutta_Volatilityforecaster,
      howpublished = {Accepted at NeurIPS 2026 Workshop TS-LIMITS: Generalization for Time Series in Tight Settings: Latency, Inference, Memory, PrIvacy and SusTainability},
      year = {2026},
      author = {Petit-Tichanné, Ulysse and Pelleriti, Nico and Zimmer, Max and Pokutta, Sebastian},
      title = {Learning the Coefficients of the Standard Volatility Forecaster}
    }

18. Zhou, Z., Li, Z., Huang, W., Li, X., Cao, C., Feng, X., Lu, X., Hu, J., Lu, M., Xie, Y., Pelleriti, N., Liu, S., Zimmer, M., Miranda, B., Yao, J., Liu, B., Koyejo, S., Pokutta, S., and Han, B. (2026). Reasoning Is More Than the Model: Harness-Aware Evaluation of Agents on Verifiable Reasoning Tasks. Accepted at ICML 2026 Workshop on AI As a Tool for Mathematics, Computer Science, and Machine Learning. [arXiv]
    [BibTeX]

    @misc{2026_ZhouEtAl_AlphaDianaVerifiableReasoning_2610-20675:1,
      howpublished = {Accepted at ICML 2026 Workshop on AI As a Tool for Mathematics, Computer Science, and Machine Learning},
      year = {2026},
      archiveprefix = {arXiv},
      eprint = {2610.20675},
      arxiv = {arXiv:2610.20675},
      primaryclass = {cs.AI},
      author = {Zhou, Zhanke and Li, Zongze and Huang, Weikai and Li, Xuan and Cao, Chentao and Feng, Xiao and Lu, Xiangyu and Hu, Jinbo and Lu, Menghan and Xie, Yi and Pelleriti, Nico and Liu, Shiyang and Zimmer, Max and Miranda, Brando and Yao, Jiangchao and Liu, Bo and Koyejo, Sanmi and Pokutta, Sebastian and Han, Bo},
      title = {Reasoning Is More Than the Model: Harness-Aware Evaluation of Agents on Verifiable Reasoning Tasks}
    }

19. Zhou, Z., Li, Z., Huang, W., Li, X., Cao, C., Feng, X., Lu, X., Hu, J., Lu, M., Xie, Y., Pelleriti, N., Liu, S., Zimmer, M., Miranda, B., Yao, J., Liu, B., Koyejo, S., Pokutta, S., and Han, B. (2026). Reasoning Is More Than the Model: Harness-Aware Evaluation of Agents on Verifiable Reasoning Tasks. Accepted at 3rd AI for Math Workshop: Toward Self-Evolving Scientific Agents @ ICML 2026. [arXiv]
    [BibTeX]

    @misc{2026_ZhouEtAl_AlphaDianaVerifiableReasoning_2610-20675:2,
      howpublished = {Accepted at 3rd AI for Math Workshop: Toward Self-Evolving Scientific Agents @ ICML 2026},
      year = {2026},
      archiveprefix = {arXiv},
      eprint = {2610.20675},
      arxiv = {arXiv:2610.20675},
      primaryclass = {cs.AI},
      author = {Zhou, Zhanke and Li, Zongze and Huang, Weikai and Li, Xuan and Cao, Chentao and Feng, Xiao and Lu, Xiangyu and Hu, Jinbo and Lu, Menghan and Xie, Yi and Pelleriti, Nico and Liu, Shiyang and Zimmer, Max and Miranda, Brando and Yao, Jiangchao and Liu, Bo and Koyejo, Sanmi and Pokutta, Sebastian and Han, Bo},
      title = {Reasoning Is More Than the Model: Harness-Aware Evaluation of Agents on Verifiable Reasoning Tasks}
    }

20. Zhou, Z., Li, Z., Huang, W., Li, X., Cao, C., Feng, X., Lu, X., Hu, J., Lu, M., Xie, Y., Pelleriti, N., Liu, S., Zimmer, M., Miranda, B., Yao, J., Liu, B., Koyejo, S., Pokutta, S., and Han, B. (2026). AlphaDiana: A System for Evaluating Reasoning Agents. Accepted at NeurIPS 2026 Workshop on Towards Test-Time Continual Learning Agents. [arXiv]
    [BibTeX]

    @misc{2026_ZhouEtAl_AlphaDianaVerifiableReasoning_2610-20675:3,
      howpublished = {Accepted at NeurIPS 2026 Workshop on Towards Test-Time Continual Learning Agents},
      year = {2026},
      archiveprefix = {arXiv},
      eprint = {2610.20675},
      arxiv = {arXiv:2610.20675},
      primaryclass = {cs.AI},
      author = {Zhou, Zhanke and Li, Zongze and Huang, Weikai and Li, Xuan and Cao, Chentao and Feng, Xiao and Lu, Xiangyu and Hu, Jinbo and Lu, Menghan and Xie, Yi and Pelleriti, Nico and Liu, Shiyang and Zimmer, Max and Miranda, Brando and Yao, Jiangchao and Liu, Bo and Koyejo, Sanmi and Pokutta, Sebastian and Han, Bo},
      title = {AlphaDiana: A System for Evaluating Reasoning Agents}
    }

21. Zhou, Z., Li, Z., Huang, W., Li, X., Cao, C., Feng, X., Lu, X., Hu, J., Lu, M., Xie, Y., Pelleriti, N., Liu, S., Zimmer, M., Miranda, B., Yao, J., Liu, B., Koyejo, S., Pokutta, S., and Han, B. (2026). AlphaDiana: A System for Evaluating Reasoning Agents. Accepted at The Sixth Workshop on Mathematical Reasoning and AI @ NeurIPS 2026. [arXiv]
    [BibTeX]

    @misc{2026_ZhouEtAl_AlphaDianaVerifiableReasoning_2610-20675:4,
      howpublished = {Accepted at The Sixth Workshop on Mathematical Reasoning and AI @ NeurIPS 2026},
      year = {2026},
      archiveprefix = {arXiv},
      eprint = {2610.20675},
      arxiv = {arXiv:2610.20675},
      primaryclass = {cs.AI},
      author = {Zhou, Zhanke and Li, Zongze and Huang, Weikai and Li, Xuan and Cao, Chentao and Feng, Xiao and Lu, Xiangyu and Hu, Jinbo and Lu, Menghan and Xie, Yi and Pelleriti, Nico and Liu, Shiyang and Zimmer, Max and Miranda, Brando and Yao, Jiangchao and Liu, Bo and Koyejo, Sanmi and Pokutta, Sebastian and Han, Bo},
      title = {AlphaDiana: A System for Evaluating Reasoning Agents}
    }

22. Głuch, G., Turan, B., Nagarajan, S. G., and Pokutta, S. (2025). The Good, the Bad and the Ugly: Meta-Analysis of Watermarks, Transferable Attacks and Adversarial Defenses. Advances in Neural Information Processing Systems, 38. Associated with NeurIPS 2025. [arXiv]
    [BibTeX]

    @inproceedings{2024_GrzegorzTuranNagarajanPokutta_Watermarksadversarialdefenses,
      year = {2025},
      booktitle = {Advances in Neural Information Processing Systems},
      series = {Advances in Neural Information Processing Systems},
      volume = {38},
      publisher = {Curran Associates},
      month = sep,
      archiveprefix = {arXiv},
      eprint = {2410.08864},
      arxiv = {arXiv:2410.08864},
      primaryclass = {cs.LG},
      author = {Głuch, Grzegorz and Turan, Berkant and Nagarajan, Sai Ganesh and Pokutta, Sebastian},
      title = {The Good, the Bad and the Ugly: Meta-Analysis of Watermarks, Transferable Attacks and Adversarial Defenses}
    }

23. Kera, H., Pelleriti, N., Ishihara, Y., Zimmer, M., and Pokutta, S. (2025). Computational Algebra with Attention: Transformer Oracles for Border Basis Algorithms. Advances in Neural Information Processing Systems, 38. Associated with NeurIPS 2025. [arXiv]
    [BibTeX]

    @inproceedings{2025_KeraEtAl_Transformeroracles_2505-23696,
      year = {2025},
      booktitle = {Advances in Neural Information Processing Systems},
      series = {Advances in Neural Information Processing Systems},
      volume = {38},
      publisher = {Curran Associates},
      month = sep,
      archiveprefix = {arXiv},
      eprint = {2505.23696},
      arxiv = {arXiv:2505.23696},
      primaryclass = {cs.LG},
      author = {Kera, Hiroshi and Pelleriti, Nico and Ishihara, Yuki and Zimmer, Max and Pokutta, Sebastian},
      title = {Computational Algebra with Attention: Transformer Oracles for Border Basis Algorithms}
    }

24. Mundinger, K., Zimmer, M., Kiem, A., Spiegel, C., and Pokutta, S. (2025). Neural Discovery in Mathematics: Do Machines Dream of Colored Planes? Proceedings of the 42nd International Conference on Machine Learning, 267, 45236–45255. Associated with ICML 2025. [URL] [arXiv]
    [BibTeX]

    @inproceedings{2025_MundingerZimmerKiemSpiegelPokutta_NeuralDiscovery,
      year = {2025},
      booktitle = {Proceedings of the 42nd International Conference on Machine Learning},
      series = {Proceedings of Machine Learning Research},
      volume = {267},
      month = jul,
      pages = {45236--45255},
      url = {https://proceedings.mlr.press/v267/mundinger25a.html},
      archiveprefix = {arXiv},
      eprint = {2501.18527},
      arxiv = {arXiv:2501.18527},
      primaryclass = {cs.LG},
      author = {Mundinger, Konrad and Zimmer, Max and Kiem, Aldo and Spiegel, Christoph and Pokutta, Sebastian},
      title = {Neural Discovery in Mathematics: Do Machines Dream of Colored Planes?}
    }

25. Turan, B., Asadulla, S., Steinmann, D., Kersting, K., Stammer, W., and Pokutta, S. (2025). Neural Concept Verifier: Scaling Prover-Verifier Games via Concept Encodings. Accepted at Actionable Interpretability Workshop at ICML 2025. [arXiv]
    [BibTeX]

    @misc{2025_TuranEtAl_Neuralconceptverifier_2507-07532:1,
      howpublished = {Accepted at Actionable Interpretability Workshop at ICML 2025},
      year = {2025},
      month = jul,
      archiveprefix = {arXiv},
      eprint = {2507.07532},
      arxiv = {arXiv:2507.07532},
      primaryclass = {cs.LG},
      author = {Turan, Berkant and Asadulla, Suhrab and Steinmann, David and Kersting, Kristian and Stammer, Wolfgang and Pokutta, Sebastian},
      title = {Neural Concept Verifier: Scaling Prover-Verifier Games via Concept Encodings}
    }

26. Pauls, J., Zimmer, M., Turan, B., Saatchi, S., Ciais, P., Pokutta, S., and Gieseke, F. (2025). Capturing Temporal Dynamics in Large-Scale Canopy Tree Height Estimation. Proceedings of the 42nd International Conference on Machine Learning, 267. Associated with ICML 2025. [arXiv]
    [BibTeX]

    @inproceedings{2025_JanEtAl_Temporalcanopyheight,
      year = {2025},
      booktitle = {Proceedings of the 42nd International Conference on Machine Learning},
      series = {Proceedings of Machine Learning Research},
      volume = {267},
      month = may,
      archiveprefix = {arXiv},
      eprint = {2501.19328},
      arxiv = {arXiv:2501.19328},
      primaryclass = {cs.LG},
      author = {Pauls, Jan and Zimmer, Max and Turan, Berkant and Saatchi, Sassan and Ciais, Philippe and Pokutta, Sebastian and Gieseke, Fabian},
      title = {Capturing Temporal Dynamics in Large-Scale Canopy Tree Height Estimation}
    }

27. Pelleriti, N., Zimmer, M., Wirth, E., and Pokutta, S. (2025). Approximating Latent Manifolds in Neural Networks via Vanishing Ideals. Proceedings of the 42nd International Conference on Machine Learning, 267. Associated with ICML 2025. [arXiv]
    [BibTeX]

    @inproceedings{2025_PelleritiZimmerWirthPokutta_Latentmanifolds,
      year = {2025},
      booktitle = {Proceedings of the 42nd International Conference on Machine Learning},
      series = {Proceedings of Machine Learning Research},
      volume = {267},
      month = may,
      archiveprefix = {arXiv},
      eprint = {2502.15051},
      arxiv = {arXiv:2502.15051},
      primaryclass = {cs.LG},
      author = {Pelleriti, Nico and Zimmer, Max and Wirth, Elias and Pokutta, Sebastian},
      title = {Approximating Latent Manifolds in Neural Networks via Vanishing Ideals}
    }

28. Zimmer, M., Spiegel, C., and Pokutta, S. (2025). Compression-aware training of neural networks using Frank–Wolfe. Mathematical Optimization for Machine Learning, 137–168. DOI: 10.1515/9783111376776-010 [arXiv]
    [BibTeX]

    @inproceedings{2022_ZimmerSpiegelPokutta_Compressionawaretraining,
      year = {2025},
      date = {2025-04-22},
      booktitle = {Mathematical Optimization for Machine Learning},
      series = {De Gruyter Proceedings in Mathematics},
      publisher = {Walter de Gruyter},
      month = apr,
      pages = {137--168},
      doi = {10.1515/9783111376776-010},
      archiveprefix = {arXiv},
      eprint = {2205.11921},
      arxiv = {arXiv:2205.11921},
      primaryclass = {cs.LG},
      author = {Zimmer, Max and Spiegel, Christoph and Pokutta, Sebastian},
      title = {Compression-aware training of neural networks using Frank–Wolfe}
    }

29. Głuch, G., Turan, B., Nagarajan, S. G., and Pokutta, S. (2025). The Good, the Bad and the Ugly: Meta-Analysis of Watermarks, Transferable Attacks and Adversarial Defenses. Accepted at ICLR 2025: Workshop on GenAI Watermarking @ ICLR 2025. [arXiv]
    [BibTeX]

    @misc{2024_GrzegorzTuranNagarajanPokutta_Watermarksadversarialdefenses:2,
      howpublished = {Accepted at ICLR 2025: Workshop on GenAI Watermarking @ ICLR 2025},
      year = {2025},
      month = mar,
      archiveprefix = {arXiv},
      eprint = {2410.08864},
      arxiv = {arXiv:2410.08864},
      primaryclass = {cs.LG},
      author = {Głuch, Grzegorz and Turan, Berkant and Nagarajan, Sai Ganesh and Pokutta, Sebastian},
      title = {The Good, the Bad and the Ugly: Meta-Analysis of Watermarks, Transferable Attacks and Adversarial Defenses}
    }

30. Lasby, M., Zimmer, M., Pokutta, S., and Schultheis, E. (2025). Compressed sparse tiles for memory-efficient unstructured and semi-structured sparsity. Accepted at Workshop on Sparsity in LLMs (SLLM): Deep Dive Into Mixture of Experts, Quantization, Hardware, and Inference. [URL]
    [BibTeX]

    @misc{2025_LasbyZimmerPokuttaSchultheis_SparseTiles,
      howpublished = {Accepted at Workshop on Sparsity in LLMs (SLLM): Deep Dive Into Mixture of Experts, Quantization, Hardware, and Inference},
      year = {2025},
      month = mar,
      url = {https://openreview.net/forum?id=iso0KV2HVq},
      author = {Lasby, Mike and Zimmer, Max and Pokutta, Sebastian and Schultheis, Erik},
      title = {Compressed sparse tiles for memory-efficient unstructured and semi-structured sparsity}
    }

31. Sadiku, S., Wagner, M., and Pokutta, S. (2025, January). GSE: Group-wise Sparse and Explainable Adversarial Attacks. International Conference on Learning Representations 2025. Associated with ICLR 2025. [arXiv]
    [BibTeX]

    @inproceedings{2023_SadikuWagnerPokutta_Groupwisesparseattacks,
      year = {2025},
      booktitle = {International Conference on Learning Representations 2025},
      publisher = {ICLR (OpenReview)},
      month = jan,
      archiveprefix = {arXiv},
      eprint = {2311.17434},
      arxiv = {arXiv:2311.17434},
      primaryclass = {cs.CV},
      author = {Sadiku, Shpresim and Wagner, Moritz and Pokutta, Sebastian},
      title = {GSE: Group-wise Sparse and Explainable Adversarial Attacks}
    }

32. Roux, C., Zimmer, M., and Pokutta, S. (2025, January). On the Byzantine-Resilience of Distillation-Based Federated Learning. International Conference on Learning Representations 2025. Associated with ICLR 2025. [arXiv]
    [BibTeX]

    @inproceedings{2024_RouxZimmerPokutta_Byzantineresilience,
      year = {2025},
      booktitle = {International Conference on Learning Representations 2025},
      publisher = {ICLR (OpenReview)},
      month = jan,
      archiveprefix = {arXiv},
      eprint = {2402.12265},
      arxiv = {arXiv:2402.12265},
      primaryclass = {cs.LG},
      author = {Roux, Christophe and Zimmer, Max and Pokutta, Sebastian},
      title = {On the Byzantine-Resilience of Distillation-Based Federated Learning}
    }

33. Sadiku, S., Wagner, M., Nagarajan, S. G., and Pokutta, S. (2025). S-CFE: Simple Counterfactual Explanations. Proceedings of The 28th International Conference on Artificial Intelligence and Statistics, 258. Associated with AISTATS 2025. [arXiv]
    [BibTeX]

    @inproceedings{2024_SadikuEtAl_Counterfactualexplanations,
      year = {2025},
      booktitle = {Proceedings of The 28th International Conference on Artificial Intelligence and Statistics},
      series = {Proceedings of Machine Learning Research},
      volume = {258},
      month = jan,
      archiveprefix = {arXiv},
      eprint = {2410.15723},
      arxiv = {arXiv:2410.15723},
      primaryclass = {cs.LG},
      author = {Sadiku, Shpresim and Wagner, Moritz and Nagarajan, Sai Ganesh and Pokutta, Sebastian},
      title = {S-CFE: Simple Counterfactual Explanations}
    }

34. Mexi, G., Besançon, M., Bolusani, S., Chmiela, A., Hoen, A., and Gleixner, A. (2025). Scylla: A Matrix-Free Fix-Propagate-and-Project Heuristic for Mixed-Integer Optimization. Operations Research Proceedings 2023, 65–72. Associated with OR 2023. DOI: 10.1007/978-3-031-58405-3_9 [arXiv]
    [BibTeX]

    @inproceedings{2023_MexiEtAl_Scyllaheuristic,
      year = {2025},
      date = {2025-09-27},
      booktitle = {Operations Research Proceedings 2023},
      series = {Lecture Notes in Operations Research},
      publisher = {Springer Science+Business Media},
      pages = {65--72},
      doi = {10.1007/978-3-031-58405-3_9},
      archiveprefix = {arXiv},
      eprint = {2307.03466},
      arxiv = {arXiv:2307.03466},
      primaryclass = {math.OC},
      author = {Mexi, Gioni and Besançon, Mathieu and Bolusani, Suresh and Chmiela, Antonia and Hoen, Alexander and Gleixner, Ambros},
      title = {Scylla: A Matrix-Free Fix-Propagate-and-Project Heuristic for Mixed-Integer Optimization}
    }

35. Fukuda, T., Kera, H., and Kawamoto, K. (2025). Adapter Merging with Centroid Prototype Mapping for Scalable Class-Incremental Learning. 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 4884–4893. Associated with CVPR 2025. DOI: 10.1109/cvpr52734.2025.00460 [arXiv]
    [BibTeX]

    @inproceedings{2024_FukudaKeraKawamoto_AdapterMerging,
      year = {2025},
      booktitle = {2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
      publisher = {Institute of Electrical and Electronics Engineers},
      pages = {4884--4893},
      doi = {10.1109/cvpr52734.2025.00460},
      archiveprefix = {arXiv},
      eprint = {2412.18219},
      arxiv = {arXiv:2412.18219},
      primaryclass = {cs.CV},
      author = {Fukuda, Takuma and Kera, Hiroshi and Kawamoto, Kazuhiko},
      title = {Adapter Merging with Centroid Prototype Mapping for Scalable Class-Incremental Learning}
    }

36. Hollender, A., Maystre, G., and Nagarajan, S. G. (2025). The Complexity of Two-Team Polymatrix Games with Independent Adversaries. International Conference on Learning Representations 2025. Associated with ICLR 2025. [arXiv]
    [BibTeX]

    @inproceedings{2024_HollenderMaystreNagarajan_Twoteampolymatrix,
      year = {2025},
      booktitle = {International Conference on Learning Representations 2025},
      publisher = {ICLR (OpenReview)},
      archiveprefix = {arXiv},
      eprint = {2409.07398},
      arxiv = {arXiv:2409.07398},
      primaryclass = {cs.GT},
      author = {Hollender, Alexandros and Maystre, Gilbert and Nagarajan, Sai Ganesh},
      title = {The Complexity of Two-Team Polymatrix Games with Independent Adversaries}
    }

37. Fackeldey, K., Kannan, A., Pokutta, S., Sharma, K., Walter, D., Walther, A., and Weiser, M. (2025). Mathematical Optimization for Machine Learning. Mathematical Optimization for Machine Learning. DOI: 10.1515/9783111376776 [URL]
    [BibTeX]

    @inproceedings{2025_FackeldeyEtAl_MathematicalOptimization,
      year = {2025},
      booktitle = {Mathematical Optimization for Machine Learning},
      series = {De Gruyter Proceedings in Mathematics},
      publisher = {Walter de Gruyter},
      doi = {10.1515/9783111376776},
      url = {https://www.degruyterbrill.com/document/doi/10.1515/9783111376776/html},
      author = {Fackeldey, Konstantin and Kannan, Aswin and Pokutta, Sebastian and Sharma, Kartikey and Walter, Daniel and Walther, Andrea and Weiser, Martin},
      title = {Mathematical Optimization for Machine Learning}
    }

38. Fayad, I., Zimmer, M., Schwartz, M., Gieseke, F., Ciais, P., Belouze, G., Brood, S., De Truchis, A., and d’Aspremont, A. (2025). DUNIA: Pixel-Sized Embeddings via Cross-Modal Alignment for Earth Observation Applications. Proceedings of the 42nd International Conference on Machine Learning, 267. Associated with ICML 2025. [arXiv]
    [BibTeX]

    @inproceedings{2025_IbrahimEtAl_DuniaCrossmodalalignment,
      year = {2025},
      booktitle = {Proceedings of the 42nd International Conference on Machine Learning},
      series = {Proceedings of Machine Learning Research},
      volume = {267},
      archiveprefix = {arXiv},
      eprint = {2502.17066},
      arxiv = {arXiv:2502.17066},
      primaryclass = {cs.CV},
      author = {Fayad, Ibrahim and Zimmer, Max and Schwartz, Martin and Gieseke, Fabian and Ciais, Philippe and Belouze, Gabriel and Brood, Sarah and De Truchis, Aurelien and d'Aspremont, Alexandre},
      title = {DUNIA: Pixel-Sized Embeddings via Cross-Modal Alignment for Earth Observation Applications}
    }

39. Głuch, G., Nagarajan, S. G., and Turan, B. (2024). Unified Taxonomy in AI Safety: Watermarks, Adversarial Defenses, and Transferable Attacks. Accepted at Workshop on Theoretical Foundations of Foundation Models (TF2M) @ ICML 2024. [URL] [arXiv]
    [BibTeX]

    @misc{2024_GrzegorzTuranNagarajanPokutta_Watermarksadversarialdefenses:1,
      howpublished = {Accepted at Workshop on Theoretical Foundations of Foundation Models (TF2M) @ ICML 2024},
      year = {2024},
      month = jul,
      url = {https://openreview.net/forum?id=WMaFRiggwV},
      archiveprefix = {arXiv},
      eprint = {2410.08864},
      arxiv = {arXiv:2410.08864},
      primaryclass = {cs.LG},
      author = {Głuch, Grzegorz and Nagarajan, Sai Ganesh and Turan, Berkant},
      title = {Unified Taxonomy in AI Safety: Watermarks, Adversarial Defenses, and Transferable Attacks}
    }

40. Pauls, J., Zimmer, M., Kelly, U. M., Schwartz, M., Saatchi, S., Ciais, P., Pokutta, S., Brandt, M., and Gieseke, F. (2024). Estimating Canopy Height at Scale. Proceedings of the 41st International Conference on Machine Learning, 235. Associated with ICML 2024. [arXiv] [code]
    [BibTeX]

    @inproceedings{2024_PaulsEtAl_Canopyheightestimation,
      year = {2024},
      booktitle = {Proceedings of the 41st International Conference on Machine Learning},
      series = {Proceedings of Machine Learning Research},
      volume = {235},
      month = may,
      archiveprefix = {arXiv},
      eprint = {2406.01076},
      arxiv = {arXiv:2406.01076},
      primaryclass = {cs.CV},
      author = {Pauls, Jan and Zimmer, Max and Kelly, Una M and Schwartz, Martin and Saatchi, Sassan and Ciais, Philippe and Pokutta, Sebastian and Brandt, Martin and Gieseke, Fabian},
      title = {Estimating Canopy Height at Scale},
      code = {https://github.com/AI4Forest/Global-Canopy-Height-Map}
    }

41. Mundinger, K., Zimmer, M., and Pokutta, S. (2024). Neural Parameter Regression for Explicit Representations of PDE Solution Operators. Accepted at ICLR 2024: AI4DifferentialEquations in Science. [URL] [arXiv]
    [BibTeX]

    @misc{2024_MundingerZimmerPokutta_Neuralparameterregression:1,
      howpublished = {Accepted at ICLR 2024: AI4DifferentialEquations in Science},
      year = {2024},
      month = mar,
      url = {https://openreview.net/forum?id=6Z0q0dzSJQ},
      archiveprefix = {arXiv},
      eprint = {2403.12764},
      arxiv = {arXiv:2403.12764},
      primaryclass = {cs.LG},
      author = {Mundinger, Konrad and Zimmer, Max and Pokutta, Sebastian},
      title = {Neural Parameter Regression for Explicit Representations of PDE Solution Operators}
    }

42. Wäldchen, S., Sharma, K., Turan, B., Zimmer, M., and Pokutta, S. (2024). Interpretability Guarantees with Merlin-Arthur Classifiers. Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, 238. Associated with AISTATS 2024. [arXiv]
    [BibTeX]

    @inproceedings{2022_WaeldchenEtAl_Interpretabilityguarantees,
      year = {2024},
      booktitle = {Proceedings of The 27th International Conference on Artificial Intelligence and Statistics},
      series = {Proceedings of Machine Learning Research},
      volume = {238},
      month = jan,
      archiveprefix = {arXiv},
      eprint = {2206.00759},
      arxiv = {arXiv:2206.00759},
      primaryclass = {cs.LG},
      author = {Wäldchen, Stephan and Sharma, Kartikey and Turan, Berkant and Zimmer, Max and Pokutta, Sebastian},
      title = {Interpretability Guarantees with Merlin-Arthur Classifiers}
    }

43. Kera, H., Ishihara, Y., Kambe, Y., Vaccon, T., and Yokoyama, K. (2024). Learning to compute Gröbner bases. Advances in Neural Information Processing Systems, 37. Associated with NeurIPS 2024. [arXiv]
    [BibTeX]

    @inproceedings{2023_KeraEtAl_Grbnerlearning,
      year = {2024},
      booktitle = {Advances in Neural Information Processing Systems},
      series = {Advances in Neural Information Processing Systems},
      volume = {37},
      publisher = {Curran Associates},
      archiveprefix = {arXiv},
      eprint = {2311.12904},
      arxiv = {arXiv:2311.12904},
      primaryclass = {math.AC},
      author = {Kera, Hiroshi and Ishihara, Yuki and Kambe, Yuta and Vaccon, Tristan and Yokoyama, Kazuhiro},
      title = {Learning to compute Gröbner bases}
    }

44. Zimmer, M., Spiegel, C., and Pokutta, S. (2024). Sparse Model Soups: A Recipe for Improved Pruning via Model Averaging. International Conference on Learning Representations 2024. Associated with ICLR 2024. [URL] [arXiv]
    [BibTeX]

    @inproceedings{2023_ZimmerSpiegelPokutta_Sparsemodelsoups,
      year = {2024},
      booktitle = {International Conference on Learning Representations 2024},
      publisher = {ICLR (OpenReview)},
      url = {https://iclr.cc/virtual/2024/poster/17433},
      archiveprefix = {arXiv},
      eprint = {2306.16788},
      arxiv = {arXiv:2306.16788},
      primaryclass = {cs.LG},
      author = {Zimmer, Max and Spiegel, Christoph and Pokutta, Sebastian},
      title = {Sparse Model Soups: A Recipe for Improved Pruning via Model Averaging}
    }

45. Kumano, S., Kera, H., and Yamasaki, T. (2024). Wide Two-Layer Networks can Learn from Adversarial Perturbations. Advances in Neural Information Processing Systems, 37, 59755–59807. Associated with NeurIPS 2024. DOI: 10.52202/079017-1909 [URL] [arXiv]
    [BibTeX]

    @inproceedings{2024_KumanoKeraYamasaki_AdversarialPerturbation,
      year = {2024},
      booktitle = {Advances in Neural Information Processing Systems},
      series = {Advances in Neural Information Processing Systems},
      volume = {37},
      publisher = {Curran Associates},
      pages = {59755--59807},
      doi = {10.52202/079017-1909},
      url = {https://proceedings.neurips.cc/paper_files/paper/2024/hash/6e0274fdb05f21654421db43cd8de042-Abstract-Conference.html},
      archiveprefix = {arXiv},
      eprint = {2410.23677},
      arxiv = {arXiv:2410.23677},
      primaryclass = {cs.LG},
      author = {Kumano, Soichiro and Kera, Hiroshi and Yamasaki, Toshihiko},
      title = {Wide Two-Layer Networks can Learn from Adversarial Perturbations}
    }

46. Mundinger, K., Pokutta, S., Spiegel, C., and Zimmer, M. (2024). Extending the Continuum of Six-Colorings. Discrete Mathematics Days 2024, 20, 178–183. Associated with DMD 2024. [URL] [arXiv]
    [BibTeX]

    @inproceedings{2024_MundingerPokuttaSpiegelZimmer_SixcoloringsExpansion:1,
      year = {2024},
      booktitle = {Discrete Mathematics Days 2024},
      series = {Obras Colectivas Ciencias},
      volume = {20},
      publisher = {Editorial Universidad de Alcalá},
      pages = {178--183},
      url = {https://dmd2024.web.uah.es/files/abstracts/paper_27.pdf},
      archiveprefix = {arXiv},
      eprint = {2404.05509},
      arxiv = {arXiv:2404.05509},
      primaryclass = {math.CO},
      author = {Mundinger, Konrad and Pokutta, Sebastian and Spiegel, Christoph and Zimmer, Max},
      title = {Extending the Continuum of Six-Colorings}
    }

47. Thuerck, D., Sofranac, B., Pfetsch, M., and Pokutta, S. (2023). Learning Cuts via Enumeration Oracles. Advances in Neural Information Processing Systems, 36, 79108–79123. Associated with NeurIPS 2023. DOI: 10.52202/075280-3461 [arXiv]
    [BibTeX]

    @inproceedings{2023_ThuerckSofranacPfetschPokutta_Learningcutsenumeration,
      year = {2023},
      booktitle = {Advances in Neural Information Processing Systems},
      series = {Advances in Neural Information Processing Systems},
      volume = {36},
      publisher = {Curran Associates},
      month = sep,
      pages = {79108--79123},
      doi = {10.52202/075280-3461},
      archiveprefix = {arXiv},
      eprint = {2305.12197},
      arxiv = {arXiv:2305.12197},
      primaryclass = {math.OC},
      author = {Thuerck, Daniel and Sofranac, Boro and Pfetsch, Marc and Pokutta, Sebastian},
      title = {Learning Cuts via Enumeration Oracles}
    }

48. Chmiela, A., Gleixner, A., Lichocki, P., and Pokutta, S. (2023). Online Learning for Scheduling MIP Heuristics. Integration of Constraint Programming, Artificial Intelligence, and Operations Research, 13884, 114–123. Associated with CPAIOR 2023. DOI: 10.1007/978-3-031-33271-5_8 [arXiv]
    [BibTeX]

    @inproceedings{2023_ChmielaGleixnerLichockiPokutta_Onlinelearningscheduling,
      year = {2023},
      date = {2023-05-23},
      booktitle = {Integration of Constraint Programming, Artificial Intelligence, and Operations Research},
      series = {Lecture Notes in Computer Science},
      volume = {13884},
      publisher = {Springer Science+Business Media},
      month = may,
      pages = {114--123},
      doi = {10.1007/978-3-031-33271-5_8},
      archiveprefix = {arXiv},
      eprint = {2304.03755},
      arxiv = {arXiv:2304.03755},
      primaryclass = {math.OC},
      author = {Chmiela, Antonia and Gleixner, Ambros and Lichocki, Pawel and Pokutta, Sebastian},
      title = {Online Learning for Scheduling MIP Heuristics}
    }

49. Zimmer, M., Spiegel, C., and Pokutta, S. (2023). How I Learned to Stop Worrying and Love Retraining. 11th International Conference on Learning Representations (ICLR 2023). Associated with ICLR 2023. [URL] [arXiv] [code]
    [BibTeX]

    @inproceedings{2021_ZimmerSpiegelPokutta_Retrainingpruning,
      year = {2023},
      booktitle = {11th International Conference on Learning Representations (ICLR 2023)},
      publisher = {ICLR (OpenReview)},
      url = {https://iclr.cc/virtual/2023/poster/10914},
      archiveprefix = {arXiv},
      eprint = {2111.00843},
      arxiv = {arXiv:2111.00843},
      primaryclass = {cs.LG},
      author = {Zimmer, Max and Spiegel, Christoph and Pokutta, Sebastian},
      title = {How I Learned to Stop Worrying and Love Retraining},
      code = {https://github.com/ZIB-IOL/BIMP}
    }

50. Macdonald, J., Besançon, M., and Pokutta, S. (2022). Interpretable Neural Networks with Frank-Wolfe: Sparse Relevance Maps and Relevance Orderings. Proceedings of the 39th International Conference on Machine Learning, 162. Associated with ICML 2022. [arXiv] [poster] [video]
    [BibTeX]

    @inproceedings{2021_MacdonaldBesanconPokutta_Interpretableneuralnetworks,
      year = {2022},
      booktitle = {Proceedings of the 39th International Conference on Machine Learning},
      series = {Proceedings of Machine Learning Research},
      volume = {162},
      month = may,
      archiveprefix = {arXiv},
      eprint = {2110.08105},
      arxiv = {arXiv:2110.08105},
      primaryclass = {cs.LG},
      author = {Macdonald, Jan and Besançon, Mathieu and Pokutta, Sebastian},
      title = {Interpretable Neural Networks with Frank-Wolfe: Sparse Relevance Maps and Relevance Orderings},
      poster = {https://pokutta.com/slides/20220712_icml_poster_interpretable_rde.pdf},
      video = {https://slideslive.com/38983588}
    }

51. Tsuji, K., Tanaka, K., and Pokutta, S. (2022). Pairwise Conditional Gradients without Swap Steps and Sparser Kernel Herding. Proceedings of the 39th International Conference on Machine Learning, 162. Associated with ICML 2022. [arXiv] [summary] [slides] [code] [video]
    [BibTeX]

    @inproceedings{2021_TsujiTanakaPokutta_Pairwiseconditionalgradients,
      year = {2022},
      booktitle = {Proceedings of the 39th International Conference on Machine Learning},
      series = {Proceedings of Machine Learning Research},
      volume = {162},
      month = may,
      archiveprefix = {arXiv},
      eprint = {2110.12650},
      arxiv = {arXiv:2110.12650},
      primaryclass = {math.OC},
      author = {Tsuji, Kazuma and Tanaka, Ken'ichiro and Pokutta, Sebastian},
      title = {Pairwise Conditional Gradients without Swap Steps and Sparser Kernel Herding},
      code = {https://github.com/ZIB-IOL/FrankWolfe.jl},
      slides = {https://pokutta.com/slides/20220624_ICML2022_BPCG.pdf},
      summary = {https://pokutta.com/blog/research/2022/05/21/bpcg-abstract.html},
      video = {https://slideslive.com/38983561}
    }

52. Wäldchen, S., Huber, F., and Pokutta, S. (2022). Training Characteristic Functions with Reinforcement Learning: XAI-methods play Connect Four. Proceedings of the 39th International Conference on Machine Learning, 162. Associated with ICML 2022. [arXiv] [poster] [video]
    [BibTeX]

    @inproceedings{2022_WaeldchenHuberPokutta_CharacteristicfunctionsReinforcementlearning,
      year = {2022},
      booktitle = {Proceedings of the 39th International Conference on Machine Learning},
      series = {Proceedings of Machine Learning Research},
      volume = {162},
      month = may,
      archiveprefix = {arXiv},
      eprint = {2202.11797},
      arxiv = {arXiv:2202.11797},
      primaryclass = {cs.LG},
      author = {Wäldchen, Stephan and Huber, Felix and Pokutta, Sebastian},
      title = {Training Characteristic Functions with Reinforcement Learning: XAI-methods play Connect Four},
      poster = {https://pokutta.com/slides/20220712_icml_poster_conn4.pdf},
      video = {https://slideslive.com/38983111}
    }

53. Chmiela, A., Khalil, E. B., Gleixner, A., Lodi, A., and Pokutta, S. (2021). Learning to Schedule Heuristics in Branch-and-Bound. Advances in Neural Information Processing Systems, 34, 24235–24246. Associated with NeurIPS 2021. [URL] [arXiv] [poster]
    [BibTeX]

    @inproceedings{2021_ChmielaEtAl_Heuristicscheduling,
      year = {2021},
      booktitle = {Advances in Neural Information Processing Systems},
      series = {Advances in Neural Information Processing Systems},
      volume = {34},
      publisher = {Curran Associates},
      month = mar,
      pages = {24235--24246},
      url = {https://proceedings.neurips.cc/paper_files/paper/2021/file/cb7c403aa312160380010ee3dd4bfc53-Paper.pdf},
      archiveprefix = {arXiv},
      eprint = {2103.10294},
      arxiv = {arXiv:2103.10294},
      primaryclass = {cs.LG},
      author = {Chmiela, Antonia and Khalil, Elias B. and Gleixner, Ambros and Lodi, Andrea and Pokutta, Sebastian},
      title = {Learning to Schedule Heuristics in Branch-and-Bound},
      poster = {https://pokutta.com/slides/20211120_poster_NeurIPS21_learningheuristics.pdf}
    }

54. Ziemke, T., Sering, L., Vargas Koch, L., Zimmer, M., Nagel, K., and Skutella, M. (2021). Flows Over Time as Continuous Limits of Packet-Based Network Simulations. Transportation Research Procedia, 52, 123–130. Associated with EWGT 2020. DOI: 10.1016/j.trpro.2021.01.014 [URL]
    [BibTeX]

    @article{2021_ZiemkeEtAl_Flowscontinuouslimits,
      year = {2021},
      date = {2021-01-01},
      journal = {Transportation Research Procedia},
      volume = {52},
      pages = {123--130},
      doi = {10.1016/j.trpro.2021.01.014},
      url = {https://sciencedirect.com/science/article/pii/S2352146521000284},
      author = {Ziemke, Theresa and Sering, Leon and Vargas Koch, Laura and Zimmer, Max and Nagel, Kai and Skutella, Martin},
      title = {Flows Over Time as Continuous Limits of Packet-Based Network Simulations}
    }

55. Zink, D., Roy, A., and Pokutta, S. (2017). Estimating Anthropometric Features from Single Depth Images with Very High Accuracy. Accepted at INFORMS Computing Society Conference.
    [BibTeX]

    @misc{2016_ZinkRoyPokutta_EstimatingAnthropometric,
      howpublished = {Accepted at INFORMS Computing Society Conference},
      year = {2017},
      author = {Zink, Daniel and Roy, Aurko and Pokutta, Sebastian},
      title = {Estimating Anthropometric Features from Single Depth Images with Very High Accuracy}
    }

56. Arumugam, K., Kadampot, I., Tahmasbi, M., Shah, S., Bloch, M., and Pokutta, S. (2017). Modulation recognition using side information and hybrid learning. 2017 IEEE International Symposium on Dynamic Spectrum Access Networks (DySPAN), 1–2. DOI: 10.1109/dyspan.2017.7920750
    [BibTeX]

    @inproceedings{2017_ArumugamKadampotTahmasbiShahBlochPokutta_ModulationRecognition,
      year = {2017},
      booktitle = {2017 IEEE International Symposium on Dynamic Spectrum Access Networks (DySPAN)},
      publisher = {Institute of Electrical and Electronics Engineers},
      pages = {1--2},
      doi = {10.1109/dyspan.2017.7920750},
      author = {Arumugam, K. and Kadampot, I. and Tahmasbi, M. and Shah, S. and Bloch, M. and Pokutta, Sebastian},
      title = {Modulation recognition using side information and hybrid learning}
    }

57. Roy, A., Xu, H., and Pokutta, S. (2017). Reinforcement Learning under Model Mismatch. Advances in Neural Information Processing Systems, 30. Associated with NeurIPS 2017. [arXiv]
    [BibTeX]

    @inproceedings{2017_RoyXuPokutta_ReinforcementLearning,
      year = {2017},
      booktitle = {Advances in Neural Information Processing Systems},
      series = {Advances in Neural Information Processing Systems},
      volume = {30},
      publisher = {Curran Associates},
      archiveprefix = {arXiv},
      eprint = {1706.04711},
      arxiv = {arXiv:1706.04711},
      primaryclass = {cs.LG},
      author = {Roy, Aurko and Xu, Huan and Pokutta, Sebastian},
      title = {Reinforcement Learning under Model Mismatch}
    }

Articles, chapters and books

1. Göß, A., Martin, A., Pokutta, S., and Sharma, K. (2026). Norm-induced cuts: outer approximation for Lipschitzian constraint functions. Journal of Global Optimization, 94(1), 35–63. DOI: 10.1007/s10898-025-01563-9 [URL] [arXiv]
   [BibTeX]

   @article{2024_AdrianMartinPokuttaSharma_Norminducedcuts,
     year = {2026},
     date = {2026-01-21},
     journal = {Journal of Global Optimization},
     month = jan,
     volume = {94},
     number = {1},
     pages = {35--63},
     doi = {10.1007/s10898-025-01563-9},
     url = {https://link.springer.com/article/10.1007/s10898-025-01563-9},
     archiveprefix = {arXiv},
     eprint = {2403.11546},
     arxiv = {arXiv:2403.11546},
     primaryclass = {math.OC},
     author = {Göß, Adrian and Martin, Alexander and Pokutta, Sebastian and Sharma, Kartikey},
     title = {Norm-induced cuts: outer approximation for Lipschitzian constraint functions}
   }

2. Dang, S., Deza, A., Gupta, S., McNicholas, P. D., Sugiyama, M., and Pokutta, S. (2026). Data science and optimization. In Data Science and Optimization (Vol. 91). Springer Science+Business Media. DOI: 10.1007/978-3-032-03844-9 [URL]
   [BibTeX]

   @incollection{2026_DangEtAl_DataScienceOptimization,
     year = {2026},
     booktitle = {Data Science and Optimization},
     series = {Fields Institute Communications},
     volume = {91},
     publisher = {Springer Science+Business Media},
     doi = {10.1007/978-3-032-03844-9},
     url = {https://doi.org/10.1007/978-3-032-03844-9},
     author = {Dang, Sanjeena and Deza, Antoine and Gupta, Swati and McNicholas, Paul D. and Sugiyama, Masashi and Pokutta, Sebastian},
     title = {Data science and optimization}
   }

3. Carderera, A., Pokutta, S., Schütte, C., and Weiser, M. (2025). An efficient first-order conditional gradient algorithm in data-driven sparse identification of nonlinear dynamics to solve sparse recovery problems under noise. Journal of Computational and Applied Mathematics, 470, 116675. DOI: 10.1016/j.cam.2025.116675 [URL] [arXiv]
   [BibTeX]

   @article{2021_CardereraPokuttaSchutteWeiser_CINDy,
     year = {2025},
     date = {2025-04-01},
     journal = {Journal of Computational and Applied Mathematics},
     month = apr,
     volume = {470},
     pages = {116675},
     doi = {10.1016/j.cam.2025.116675},
     url = {https://www.sciencedirect.com/science/article/abs/pii/S037704272500189X},
     archiveprefix = {arXiv},
     eprint = {2101.02630},
     arxiv = {arXiv:2101.02630},
     primaryclass = {math.DS},
     author = {Carderera, Alejandro and Pokutta, Sebastian and Schütte, Christof and Weiser, Martin},
     title = {An efficient first-order conditional gradient algorithm in data-driven sparse identification of nonlinear dynamics to solve sparse recovery problems under noise}
   }

4. Vu‐Han, T. L., Sunkara, V., Bermudez‐Schettino, R., Schwechten, J., Runge, R., Perka, C., Winkler, T., Pokutta, S., Weiß, C., and Pumberger, M. (2025). Feature Engineering for the Prediction of Scoliosis in 5q‐Spinal Muscular Atrophy. Journal of Cachexia Sarcopenia and Muscle, 16(1), e13599. DOI: 10.1002/jcsm.13599 [URL]
   [BibTeX]

   @article{2024_Pokutta_PredictionScoliosis,
     year = {2025},
     journal = {Journal of Cachexia Sarcopenia and Muscle},
     month = feb,
     volume = {16},
     number = {1},
     pages = {e13599},
     doi = {10.1002/jcsm.13599},
     url = {https://onlinelibrary.wiley.com/doi/pdf/10.1002/jcsm.13599},
     author = {Vu‐Han, Tu‐Lan and Sunkara, Vikram and Bermudez‐Schettino, Rodrigo and Schwechten, Jakob and Runge, Robin and Perka, Carsten and Winkler, Tobias and Pokutta, Sebastian and Weiß, Claudia and Pumberger, Matthias},
     title = {Feature Engineering for the Prediction of Scoliosis in 5q‐Spinal Muscular Atrophy}
   }

5. Mundinger, K., Pokutta, S., Spiegel, C., and Zimmer, M. (2024). Extending the Continuum of Six-Colorings. Geombinatorics, XXXIV(1), 20–29. [URL] [arXiv]
   [BibTeX]

   @article{2024_MundingerPokuttaSpiegelZimmer_SixcoloringsExpansion,
     year = {2024},
     date = {2024-07-01},
     journal = {Geombinatorics},
     month = jul,
     volume = {XXXIV},
     number = {1},
     pages = {20--29},
     url = {https://geombina.uccs.edu/past-issues/volume-xxxiv},
     archiveprefix = {arXiv},
     eprint = {2404.05509},
     arxiv = {arXiv:2404.05509},
     primaryclass = {math.CO},
     author = {Mundinger, Konrad and Pokutta, Sebastian and Spiegel, Christoph and Zimmer, Max},
     title = {Extending the Continuum of Six-Colorings}
   }

6. Aigner, K.-M., Bärmann, A., Braun, K., Liers, F., Pokutta, S., Schneider, O., Sharma, K., and Tschuppik, S. (2023). Data-Driven Distributionally Robust Optimization over Time. INFORMS Journal on Optimization, 5(4), 376–394. DOI: 10.1287/ijoo.2023.0091 [URL] [arXiv]
   [BibTeX]

   @article{2023_KevinEtAl_Datadrivendistributionallyrobust,
     year = {2023},
     date = {2023-10-01},
     journal = {INFORMS Journal on Optimization},
     month = oct,
     volume = {5},
     number = {4},
     pages = {376--394},
     doi = {10.1287/ijoo.2023.0091},
     url = {https://pubsonline.informs.org/doi/pdf/10.1287/ijoo.2023.0091},
     archiveprefix = {arXiv},
     eprint = {2304.05377},
     arxiv = {arXiv:2304.05377},
     primaryclass = {math.OC},
     author = {Aigner, Kevin-Martin and Bärmann, Andreas and Braun, Kristin and Liers, Frauke and Pokutta, Sebastian and Schneider, Oskar and Sharma, Kartikey and Tschuppik, Sebastian},
     title = {Data-Driven Distributionally Robust Optimization over Time}
   }

7. Bienstock, D., Muñoz, G., and Pokutta, S. (2023). Principled deep neural network training through linear programming. Discrete Optimization, 49, 100795. DOI: 10.1016/j.disopt.2023.100795 [URL] [arXiv] [summary]
   [BibTeX]

   @article{2018_DanielGonzaloPokutta_Polyhedraltraining,
     year = {2023},
     date = {2023-08-01},
     journal = {Discrete Optimization},
     month = aug,
     volume = {49},
     pages = {100795},
     doi = {10.1016/j.disopt.2023.100795},
     url = {https://www.sciencedirect.com/science/article/abs/pii/S1572528623000373},
     archiveprefix = {arXiv},
     eprint = {1810.03218},
     arxiv = {arXiv:1810.03218},
     primaryclass = {cs.LG},
     author = {Bienstock, Daniel and Muñoz, Gonzalo and Pokutta, Sebastian},
     title = {Principled deep neural network training through linear programming},
     summary = {https://www.pokutta.com/blog/research/2018/10/12/DNN-learning-lp-abstract.html}
   }

8. Kruser, J., Sharma, K., Holl, J., and Nohadani, O. (2023). Identifying Patterns of Medical Intervention in Acute Respiratory Failure: A Retrospective Observational Study. Critical Care Explorations, 5(10), e0984. DOI: 10.1097/cce.0000000000000984
   [BibTeX]

   @article{2023_KruserSharmaHollNohadani_Medicalinterventionpatterns,
     year = {2023},
     date = {2023-09-30},
     journal = {Critical Care Explorations},
     volume = {5},
     number = {10},
     pages = {e0984},
     doi = {10.1097/cce.0000000000000984},
     author = {Kruser, Jacqueline and Sharma, Kartikey and Holl, Jane and Nohadani, Omid},
     title = {Identifying Patterns of Medical Intervention in Acute Respiratory Failure: A Retrospective Observational Study}
   }

9. Kossen, T., Hirzel, M., Madai, V. I., Boenisch, F., Hennemuth, A., Hildebrand, K., Pokutta, S., Sharma, K., Hilbert, A., Sobesky, J., Galinovic, I., Khalil, A. A., Fiebach, J. B., and Frey, D. (2022). Towards sharing brain images: differentially private TOF-MRA images with segmentation labels using generative adversarial networks. Frontiers in Artificial Intelligence, 5, 813842. DOI: 10.3389/frai.2022.813842
   [BibTeX]

   @article{2022_KossenEtAl_DifferentiallyPrivateBrain,
     year = {2022},
     date = {2022-05-02},
     journal = {Frontiers in Artificial Intelligence},
     month = may,
     volume = {5},
     pages = {813842},
     doi = {10.3389/frai.2022.813842},
     author = {Kossen, Tabea and Hirzel, Manuel and Madai, Vince Istvan and Boenisch, Franziska and Hennemuth, Anja and Hildebrand, Kristian and Pokutta, Sebastian and Sharma, Kartikey and Hilbert, Adam and Sobesky, Jan and Galinovic, Ivana and Khalil, Ahmed Abdelrahim and Fiebach, Jochen B. and Frey, Dietmar},
     title = {Towards sharing brain images: differentially private TOF-MRA images with segmentation labels using generative adversarial networks}
   }

10. Nohadani, O., and Sharma, K. (2022). Optimization Under Connected Uncertainty. INFORMS Journal on Optimization, 4(3), 326–346. DOI: 10.1287/ijoo.2021.0067 [arXiv]
    [BibTeX]

    @article{2022_NohadaniSharma_Connecteduncertainty,
      year = {2022},
      date = {2022-01-24},
      journal = {INFORMS Journal on Optimization},
      volume = {4},
      number = {3},
      pages = {326--346},
      doi = {10.1287/ijoo.2021.0067},
      archiveprefix = {arXiv},
      eprint = {2202.10602},
      arxiv = {arXiv:2202.10602},
      primaryclass = {math.OC},
      author = {Nohadani, Omid and Sharma, Kartikey},
      title = {Optimization Under Connected Uncertainty}
    }

11. Pokutta, S. (2020). Mathematik, Machine Learning und Artificial Intelligence. Mitteilungen Der Deutschen Mathematiker-Vereinigung, 28(4), 213–219. DOI: 10.1515/dmvm-2020-0067 [URL]
    [BibTeX]

    @article{2021_Pokutta_MathematikMachineLearning,
      year = {2020},
      journal = {Mitteilungen der Deutschen Mathematiker-Vereinigung},
      month = dec,
      volume = {28},
      number = {4},
      pages = {213--219},
      doi = {10.1515/dmvm-2020-0067},
      note = {(German)},
      url = {https://app.box.com/s/8u6fsucm78e1shyyzoghxar40f7xk6ni},
      author = {Pokutta, Sebastian},
      title = {Mathematik, Machine Learning und Artificial Intelligence}
    }

12. Klus, S., and Gelß, P. (2019). Tensor-Based Algorithms for Image Classification. Algorithms, 12(11), 240. DOI: 10.3390/a12110240 [URL] [arXiv]
    [BibTeX]

    @article{2019_KlusGelss_Tensoralgorithmsclassification,
      year = {2019},
      date = {2019-11-09},
      journal = {Algorithms},
      volume = {12},
      number = {11},
      pages = {240},
      doi = {10.3390/a12110240},
      url = {https://mdpi.com/1999-4893/12/11/240},
      archiveprefix = {arXiv},
      eprint = {1910.02150},
      arxiv = {arXiv:1910.02150},
      primaryclass = {cs.LG},
      author = {Klus, Stefan and Gelß, Patrick},
      title = {Tensor-Based Algorithms for Image Classification}
    }