I am an NSF TRIPODS Postdoctoral Fellow at the University of Illinois at Urbana-Champaign. I am affiliated with Illinois Institute of Data Science and Dynamical Systems. My research interests lie in theoretical machine learning, optimization and applied probability, with a focus on:

• theoretical and algorithmic foundations of reinforcement learning,
• deep learning theory.

Selected Papers

• Finite-Time Analysis of Entropy-Regularized Neural Natural Actor-Critic [paper]
  Semih Cayci, Niao He, R. Srikant
  
• Sample Complexity and Overparameterization Bounds for TD Learning with Neural Network Approximation [paper]
  Semih Cayci, Siddhartha Satpathi, Niao He, R. Srikant
  ICML Workshop on Overparameterization 2021
• Convergence of Entropy-Regularized Natural Policy Gradient Methods with Linear Function Approximation [paper]
  Semih Cayci, Niao He, R. Srikant
  ICML Workshop on Reinforcement Learning Theory 2021
• A Lyapunov-Based Methodology for Constrained Optimization with Bandit Feedback
  Semih Cayci, Yilin Zheng, Atilla Eryilmaz
  AAAI 2022
  [paper]
• Group-Fair Online Allocation in Continuous Time
  Semih Cayci, Swati Gupta, Atilla Eryilmaz
  NeurIPS 2020
  [paper]
• Budget-Constrained Bandits over General Cost and Reward Distributions
  Semih Cayci, Atilla Eryilmaz, R. Srikant
  AISTATS 2020
  [paper]
• Learning to Control Renewal Processes with Bandit Feedback
  Semih Cayci, Atilla Eryilmaz, R. Srikant
  ACM SIGMETRICS 2019
  [paper]