Sotabase

Career

· Assistant Professor for Mathematics of Machine Learning, RWTH Aachen University2022–
· NSF TRIPODS Postdoctoral Research Fellow, University of Illinois at Urbana-Champaign2020–2022
· Doctor of Philosophy in Electrical and Computer Engineering, The Ohio State University2014–2020
· Master's Degree, Bilkent University
· Professor, RWTH Aachen

Publications (35)

Budget-Constrained Bandits over General Cost and Reward Distributions
International Conference on Artificial Intelligence and Statistics · 2020
37
cited
Linear Convergence of Entropy-Regularized Natural Policy Gradient with Linear Function Approximation
arXiv.org · 2021
35
cited
Policy Mirror Ascent for Efficient and Independent Learning in Mean Field Games
International Conference on Machine Learning · 2022
33
cited
Learning to Control Renewal Processes with Bandit Feedback
Measurement and Modeling of Computer Systems · 2019
23
cited
Group-Fair Online Allocation in Continuous Time
Neural Information Processing Systems · 2020
22
cited
Finite-Time Analysis of Entropy-Regularized Neural Natural Actor-Critic Algorithm
Trans. Mach. Learn. Res. · 2022
21
cited
Nonbinary Polar Coding for Multilevel Modulation
Optical Fiber Communications Conference and Exhibition · 2019
14
cited
Learning for serving deadline-constrained traffic in multi-channel wireless networks
International Symposium on Modeling and Optimization in Mobile, Ad-Hoc and Wireless Networks · 2017
13
cited
Convergence of Entropy-Regularized Natural Policy Gradient with Linear Function Approximation
SIAM Journal on Optimization · 2024
12
cited
A Lyapunov-Based Methodology for Constrained Optimization with Bandit Feedback
AAAI Conference on Artificial Intelligence · 2021
11
cited
Sample Complexity and Overparameterization Bounds for Temporal-Difference Learning With Neural Network Approximation
IEEE Transactions on Automatic Control · 2021
11
cited
Polar code construction for non-binary source alphabets
Signal Processing and Communications Applications Conference · 2012
10
cited
Convergence of Gradient Descent for Recurrent Neural Networks: A Nonasymptotic Analysis
SIAM Journal on Mathematics of Data Science · 2024
8
cited
Finite-Time Analysis of Natural Actor-Critic for POMDPs
SIAM Journal on Mathematics of Data Science · 2022
6
cited
Continuous-Time Multi-Armed Bandits with Controlled Restarts
arXiv.org · 2020
5
cited
Hardware-Efficient Quantized Polar Decoding with Optimized Lookup Table
2019 24th OptoElectronics and Communications Conference (OECC) and 2019 International Conference on Photonics in Switching and Computing (PSC) · 2019
5
cited
Lossless polar compression of q-ary sources
2013 IEEE International Symposium on Information Theory · 2013
5
cited
Provably Robust Temporal Difference Learning for Heavy-Tailed Rewards
Neural Information Processing Systems · 2023
5
cited
Fisher-Rao Gradient Flows of Linear Programs and State-Action Natural Policy Gradients
arXiv.org · 2024
4
cited
Learning to Control Partially Observed Systems with Finite Memory
arXiv.org · 2022
4
cited
Sotabase
Semih Cayci | Researcher Profile | Sotabase | Sotabase