Semih Cayci

According to our database, Semih Cayci authored at least 21 papers between 2012 and 2024.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2024

Fisher-Rao Gradient Flows of Linear Programs and State-Action Natural Policy Gradients.

Johannes Müller, Semih Cayci, Guido Montúfar

CoRR, 2024

Convergence of Gradient Descent for Recurrent Neural Networks: A Nonasymptotic Analysis.

Semih Cayci, Atilla Eryilmaz

CoRR, 2024

2023

Sample Complexity and Overparameterization Bounds for Temporal-Difference Learning With Neural Network Approximation.

Semih Cayci, Siddhartha Satpathi, Niao He, R. Srikant

IEEE Trans. Autom. Control., May, 2023

Provably Robust Temporal Difference Learning for Heavy-Tailed Rewards.

Semih Cayci, Atilla Eryilmaz

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Policy Mirror Ascent for Efficient and Independent Learning in Mean Field Games.

Batuhan Yardim, Semih Cayci, Matthieu Geist, Niao He

Proceedings of the International Conference on Machine Learning, 2023

2022

Finite-Time Analysis of Entropy-Regularized Neural Natural Actor-Critic Algorithm.

Semih Cayci, Niao He, R. Srikant

CoRR, 2022

Learning to Control Partially Observed Systems with Finite Memory.

Semih Cayci, Niao He, R. Srikant

CoRR, 2022

A Lyapunov-Based Methodology for Constrained Optimization with Bandit Feedback.

Semih Cayci, Yilin Zheng, Atilla Eryilmaz

Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022

2021

Linear Convergence of Entropy-Regularized Natural Policy Gradient with Linear Function Approximation.

Semih Cayci, Niao He, R. Srikant

CoRR, 2021

Sample Complexity and Overparameterization Bounds for Projection-Free Neural TD Learning.

Semih Cayci, Siddhartha Satpathi, Niao He, R. Srikant

CoRR, 2021

2020

Continuous-Time Multi-Armed Bandits with Controlled Restarts.

Semih Cayci, Atilla Eryilmaz, R. Srikant

CoRR, 2020

Group-Fair Online Allocation in Continuous Time.

Semih Cayci, Swati Gupta, Atilla Eryilmaz

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Budget-Constrained Bandits over General Cost and Reward Distributions.

Semih Cayci, Atilla Eryilmaz, R. Srikant

Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020

2019

Optimal Learning for Dynamic Coding in Deadline-Constrained Multi-Channel Networks.

Semih Cayci, Atilla Eryilmaz

IEEE/ACM Trans. Netw., 2019

Learning to Control Renewal Processes with Bandit Feedback.

Semih Cayci, Atilla Eryilmaz, R. Srikant

Proc. ACM Meas. Anal. Comput. Syst., 2019

Hardware-Efficient Quantized Polar Decoding with Optimized Lookup Table.

Toshiaki Koike-Akino, Ye Wang, Semih Cayci, David S. Millar, Keisuke Kojima, Kieran Parsons

Proceedings of the 2019 24th OptoElectronics and Communications Conference (OECC) and 2019 International Conference on Photonics in Switching and Computing (PSC), 2019

Nonbinary Polar Coding for Multilevel Modulation.

Semih Cayci, Toshiaki Koike-Akino, Ye Wang

Proceedings of the Optical Fiber Communications Conference and Exhibition, 2019

2017

Learning for serving deadline-constrained traffic in multi-channel wireless networks.

Semih Cayci, Atilla Eryilmaz

Proceedings of the 15th International Symposium on Modeling and Optimization in Mobile, 2017

2016

On the Multi-Channel Capacity Gains of Millimeter-Wave Communication.

Semih Cayci, Atilla Eryilmaz

Proceedings of the 2016 IEEE Global Communications Conference, 2016

2013

Lossless polar compression of g-ary sources.

Semih Cayci, Orhan Arikan

Proceedings of the 2013 IEEE International Symposium on Information Theory, 2013

2012

Polar code construction for non-binary source alphabets.

Semih Cayci, Orhan Arikan, Erdal Arikan

Proceedings of the 20th Signal Processing and Communications Applications Conference, 2012