I am an NSF TRIPODS Postdoctoral Research Fellow at University of Illinois at Urbana-Champaign, working with Prof. R. Srikant and Prof. Niao He. My research interests include theoretical machine learning, reinforcement learning, online learning, multi-armed bandits, and applied probability.

Selected Publications:

• S. Cayci, S. Satpathi, N. He, R. Srikant, "Sample Complexity and Overparameterization Bounds for Temporal Difference Learning with Neural Network Approximation", arXiv:2103.01391 [link]
  

• S. Cayci, N. He, R. Srikant, "Linear Convergence of Entropy-Regularized Natural Policy Gradient with Linear Function Approximation", arXiv:2106.04096 [link]
  

• S. Cayci, S. Gupta, A. Eryilmaz, "Group-Fair Online Allocation in Continuous Time", Proceedings of NeurIPS 2020 [link]

• S. Cayci, A. Eryilmaz, R. Srikant, "Budget-Constrained Bandits over General Cost and Reward Distributions", Proceedings of AISTATS 2020 [link][slides]

• S. Cayci, A. Eryilmaz, R. Srikant, "Learning to Control Renewal Processes with Bandit Feedback", Proceedings of ACM SIGMETRICS 2019 [link]