I am a tenure-track Assistant Professor for Mathematics of Machine Learning in the Department of Mathematics at RWTH Aachen University.

My research interests lie in theoretical machine learning, optimization and probability theory, with a focus on:

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

Selected Papers

• Sample Complexity and Overparameterization Bounds for TD Learning with Neural Network Approximation [paper]
  Semih Cayci, Siddhartha Satpathi, Niao He, R. Srikant
  IEEE Transactions on Automatic Control, May 2023.
  
• 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 [paper]
  Semih Cayci, Yilin Zheng, Atilla Eryilmaz
  AAAI 2022
  

Teaching

• MATH 11.70010 - Mathematical Foundations of Reinforcement Learning (Winter 2022/23)
  

Miscellaneous

• Prior to joining RWTH Aachen, I was an NSF TRIPODS Postdoctoral Fellow at the University of Illinois at Urbana-Champaign. I was affiliated with Illinois Institute of Data Science and Dynamical Systems and ODI Group at ETH Zurich.
  
• I received my PhD from the Ohio State University.