# David Martínez-Rubio

I am mainly interested in optimization and online learning with a focus on high dimensional problems. I have worked on non-linear convex and non-convex problems, Riemannian geodesically convex optimization, accelerated algorithms, PageRank, packing, and bandit problems.

## 📬 Contact

- office
- Room 3107 at
ZIB

Room MA 604 at TUB - martinez-rubio (at) zib.de
- homepage
- damaru2.github.io
- languages
- English, Spanish, and Toki Pona

## 🎓 Curriculum vitae

- since 2022
- Researcher at ZIB
- Jan 2022
- Ph.D. in Computer Science at Oxford
- Aug 2017
- M.Sc. in Mathematics and Foundations of Computer Science at Oxford
- Jul 2016
- B.Sc. in Computer Science and Engineering at UCM
- Jul 2016
- B.Sc. in Mathematics at UCM

## 📝 Publications and preprints

### Preprints

- Martínez-Rubio, D., Roux, C., Criscitiello, C., and Pokutta, S. (2023).
*Accelerated Riemannian Min-Max Optimization Ensuring Bounded Geometric Penalties*. [arXiv]## [BibTeX]

- Scieur, D., Kerdreux, T., Martínez-Rubio, D., d’Aspremont, A., and Pokutta, S. (2023).
*Strong Convexity of Sets in Riemannian Manifolds*. [arXiv]## [BibTeX]

### Conference proceedings

- Martínez-Rubio, D., Roux, C., and Pokutta, S. (2024). Convergence and Trade-offs in Riemannian Gradient Descent and Riemannian Proximal Point.
*Proceedings of International Conference on Machine Learning*. [arXiv]## [BibTeX]

- Criscitiello, C., Martínez-Rubio, D., and Boumal, N. (2023). Open Problem: Polynomial Linearly-convergent Method for G-convex Optimization?
*Proceedings of Annual Conference on Learning Theory*. [arXiv]## [BibTeX]

- Martínez-Rubio, D., and Pokutta, S. (2023). Accelerated Riemannian Optimization: Handling Constraints with a Prox to Bound Geometric Penalties.
*Proceedings of Annual Conference on Learning Theory*. [URL] [arXiv] [poster]## [BibTeX]

- Martínez-Rubio, D., Wirth, E., and Pokutta, S. (2023). Accelerated and Sparse Algorithms for Approximate Personalized PageRank and Beyond.
*Proceedings of Annual Conference on Learning Theory*. [arXiv]## [BibTeX]

- Criado, F., Martínez-Rubio, D., and Pokutta, S. (2022). Fast Algorithms for Packing Proportional Fairness and Its Dual.
*Proceedings of Conference on Neural Information Processing Systems*. [arXiv] [poster]## [BibTeX]

## 🔬 Projects

Sparsity and Sample-size Efficiency in Structured Learning

In this project, we study algorithms that promote sparsity. We develop PageRank optimization algorithms that scale with solution sparsity and investigate Riemannian optimization using manifold geometry. Additionally, we develop algorithms for efficient fair resource allocation based on established fairness axioms.

MATH+ AA5-1

Jan 2022 to Dec 2023

2

7