Melis Ilayda Bal

^{^{mbal [at] tuebingen [dot] mpg [dot] de}}

Hello!

I am a second-year PhD candidate at the Max Planck Institute for Intelligent Systems, in Tübingen, Germany, and a doctoral fellow through the Amazon-MPI Science Hub.

I am co-advised by Michael Muehlebach and Volkan Cevher.

I hold an M.Sc. in Operations Research and a B.Sc. in Industrial Engineering, with a minor in Computer Engineering, from Middle East Technical University (METU).

My research focuses on optimization for machine learning, specifically aimed at developing techniques that enhance the robustness and training efficiency of machine learning models. Previously, I delved into the intersection of algorithmic decision-making and multi-agent systems, examining the intricate interplay between game theory and stochastic optimization. This exploration spanned various contexts, including reinforcement learning, Bayesian optimization, and protein design.

news

Jan 31, 2025	ICLR 2025: Two papers accepted! I will present our work on Adversarial Training for Defense Against Label Poisoning Attacks and Optimistic Games for Combinatorial Bayesian Optimization with Application to Protein Design, see you in Singapore!
Jan 25, 2024	Passed my PhD Qualifying Exam! Thanks to committee members Dr. Michael Muehlebach, Prof. Andreas Krause and Dr. Manuel Gomez Rodriguez.
Dec 18, 2023	Joined Learning and Dynamical Systems Group (LDS) at MPI Intelligent Systems led by Dr. Michael Muehlebach.
Mar 1, 2023	Joined Learning and Adaptive Systems (LAS) - Interactive Learning Group at ETH Zurich & MPI Intelligent Systems led by Prof. Andreas Krause.
Sep 1, 2022	Started CS@maxplanck doctoral program at the Max Planck Institute for Software Systems

selected publications

2025

ICLR 2025

Adversarial Training for Defense Against Label Poisoning Attacks

Melis Ilayda Bal, Volkan Cevher, and Michael Muehlebach

In International Conference on Learning Representations, 2025

Bib HTML

@article{mib-floral,
  author = {Bal, Melis Ilayda and Cevher, Volkan and Muehlebach, Michael},
  title = {Adversarial Training for Defense Against Label Poisoning Attacks},
  journal = {In International Conference on Learning Representations},
  year = {2025},
}

ICLR 2025

Optimistic Games for Combinatorial Bayesian Optimization with Applications to Protein Design

Melis Ilayda Bal, Pier G. Sessa, Mojmir Mutny, and Andreas Krause

In International Conference on Learning Representations, 2025

Preliminary version presented at NeurIPS 2023 ReALML Workshop, [Best paper award finalist*, Spotlight talk*]

Bib HTML

@article{mib-gameopt,
  author = {Bal, Melis Ilayda and Sessa, Pier G. and Mutny, Mojmir and Krause, Andreas},
  title = {Optimistic Games for Combinatorial Bayesian Optimization with Applications to Protein Design},
  journal = {In International Conference on Learning Representations},
  year = {2025},
  note = {Preliminary version presented at NeurIPS 2023 ReALML Workshop, [Best paper award finalist*, Spotlight talk*]},
}