A photo taken at Marble Canyon, Arizona.

Ege C. Kaya

PhD Candidate, Electrical and Computer Engineering · Purdue University

Email: kayae [at] purdue (dot) edu · Google Scholar

About Me

I’m a PhD candidate in the Department of Electrical and Computer Engineering at Purdue University, advised by Prof. Abolfazl Hashemi. I previously earned my B.Sc. in Computer Engineering and my B.Sc. in Mathematics from Boğaziçi University. My research interests include reinforcement learning and optimization for deep learning.

Papers

Preprints

  • Submodular maximization approaches for equitable client selection in federated learning — Jiménez, A. C. C., Kaya, E. C., Ye, L., & Hashemi, A. (2024). [URL]

Conference Proceedings

  • Equitable Client Selection in Federated Learning via Truncated Submodular Maximization — Jiménez, A. C. C., Kaya, E. C., Ye, L., & Hashemi, A. IEEE 63rd Conference on Decision and Control (CDC) , 2024. [URL]
  • Relative entropy regularization for robust submodular multi-task subset selection — Kaya, E. C., & Hashemi, A. 59th Annual Allerton Conference on Communication, Control, and Computing (Allerton), 2023. [URL]
  • Communication-constrained exchange of zeroth-order information with application to collaborative target tracking — Kaya, E. C., Sahin, M. B., & Hashemi, A. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023. [URL]
  • High probability guarantees for submodular maximization via boosted stochastic greedy — Jiménez, A. C. C., Kaya, E. C., & Hashemi, A. 57th Asilomar Conference on Signals, Systems, and Computers, 2023. [URL]

Journal Publications

  • Randomized greedy methods for weak submodular sensor selection with robustness considerations — Kaya, E. C., Hibbard, M., Tanaka, T., Topcu, U., & Hashemi, A. Automatica, 2025. [URL]
  • Localized distributional robustness in submodular multi-task subset selection — Kaya, E. C., & Hashemi, A. IEEE Transactions on Signal Processing, 2024. [URL]
  • Communication-efficient zeroth-order distributed online optimization: Algorithm, theory, and applications — Kaya, E. C., Sahin, M. B., & Hashemi, A. IEEE Access, 2023. [URL]

Workshop Papers

  • Beyond marginals: Capturing correlated returns through joint distributional reinforcement learning — Kaya, E. C., Ghasemi, M., & Hashemi, A. NeurIPS 2025 Workshop: Second Workshop on Aligning Reinforcement Learning Experimentalists and Theorists, 2025.