Sai Ganesh Nagarajan

I am interested in studying fundamental questions in machine learning problems motivated by realistic constraints in applications: such as data truncation/censoring and data dependence, presence of agents (algorithms) that adapt over time and compete for resources. More recently, I am interested in understanding algorithms for discrete and combinatorial optimization problems when having access to ML predictors.

📬 Contact

office
Room 3024 at ZIB
e-mail
homepage
sites.google.com/view/sgnagarajan/home

🎓 Curriculum vitae

since 2023
Researcher at ZIB
Feb 2021
Ph.D. in Engineering Systems and Design at Singapore University of Technology and Design
Jun 2014
B.Engg. in Computer Engineering at National University of Singapore

📝 Publications and preprints

Preprints

  1. Głuch, G., Turan, B., Nagarajan, S. G., and Pokutta, S. (2024). The Good, the Bad and the Ugly: Watermarks, Transferable Attacks and Adversarial Defenses. [arXiv]
    [BibTeX]
    @misc{2024_GrzegorzTuranNagarajanPokutta_Watermarksadversarialdefenses,
      archiveprefix = {arXiv},
      eprint = {2410.08864},
      primaryclass = {cs.LG},
      year = {2024},
      author = {Głuch, Grzegorz and Turan, Berkant and Nagarajan, Sai Ganesh and Pokutta, Sebastian},
      title = {The Good, the Bad and the Ugly: Watermarks, Transferable Attacks and Adversarial Defenses}
    }
  2. Sadiku, S., Wagner, M., Nagarajan, S. G., and Pokutta, S. (2024). S-CFE: Simple Counterfactual Explanations. [arXiv]
    [BibTeX]
    @misc{2024_SadikuEtAl_Counterfactualexplanations,
      archiveprefix = {arXiv},
      eprint = {2410.15723},
      primaryclass = {cs.LG},
      year = {2024},
      author = {Sadiku, Shpresim and Wagner, Moritz and Nagarajan, Sai Ganesh and Pokutta, Sebastian},
      title = {S-CFE: Simple Counterfactual Explanations}
    }