Budget-constrained bandits over general cost and reward distributions S Cayci, A Eryilmaz, R Srikant International Conference on Artificial Intelligence and Statistics. PMLR …, 2020 | 35 | 2020 |
Convergence of entropy-regularized natural policy gradient with linear function approximation S Cayci, N He, R Srikant SIAM Journal on Optimization, 2024 | 33 | 2024 |
Policy mirror ascent for efficient and independent learning in mean field games B Yardim, S Cayci, M Geist, N He International Conference on Machine Learning, 39722-39754, 2023 | 28 | 2023 |
Learning to control renewal processes with bandit feedback S Cayci, A Eryilmaz, R Srikant Proceedings of the ACM on Measurement and Analysis of Computing Systems 3 (2 …, 2019 | 27 | 2019 |
Group-fair online allocation in continuous time S Cayci, S Gupta, A Eryilmaz Advances in Neural Information Processing Systems 33, 13750--13761, 2020 | 21 | 2020 |
Nonbinary polar coding for multilevel modulation S Cayci, T Koike-Akino, Y Wang 2019 Optical Fiber Communications Conference and Exhibition (OFC), 1-3, 2019 | 20 | 2019 |
Finite-time analysis of entropy-regularized neural natural actor-critic algorithm S Cayci, N He, R Srikant Transactions on Machine Learning Research, 2024 | 17 | 2024 |
Learning for serving deadline-constrained traffic in multi-channel wireless networks S Cayci, A Eryilmaz 2017 15th International Symposium on Modeling and Optimization in Mobile, Ad …, 2017 | 14 | 2017 |
Sample Complexity and Overparameterization Bounds for Temporal Difference Learning with Neural Network Approximation S Cayci, S Satpathi, N He, R Srikant IEEE Transactions on Automatic Control 68 (May), 2023 | 12* | 2023 |
Polar code construction for non-binary source alphabets S Çaycı, O Arıkan, E Arıkan 2012 20th Signal Processing and Communications Applications Conference (SIU …, 2012 | 12 | 2012 |
A Lyapunov-Based Methodology for Constrained Optimization with Bandit Feedback S Cayci, Y Zheng, A Eryilmaz Proceedings of the AAAI Conference on Artificial Intelligence 36 (4), 3716--3723, 2022 | 8 | 2022 |
Continuous-time multi-armed bandits with controlled restarts S Cayci, A Eryilmaz, R Srikant arXiv preprint arXiv:2007.00081, 2020 | 6 | 2020 |
Hardware-efficient quantized polar decoding with optimized lookup table T Koike-Akino, Y Wang, S Cayci, DS Millar, K Kojima, K Parsons 2019 24th OptoElectronics and Communications Conference (OECC) and 2019 …, 2019 | 6 | 2019 |
Lossless polar compression of q-ary sources S Çayci, O Arikan 2013 IEEE International Symposium on Information Theory, 1132-1136, 2013 | 5 | 2013 |
Finite-time analysis of Natural Actor-Critic for POMDPs S Cayci, N He, R Srikant SIAM Journal on Mathematics of Data Science 6 (4), 869-896, 2024 | 4* | 2024 |
On the multi-channel capacity gains of millimeter-wave communication S Cayci, A Eryilmaz 2016 IEEE Global Communications Conference (GLOBECOM), 1-6, 2016 | 4 | 2016 |
Stateless Mean-Field Games: A Framework for Independent Learning with Large Populations B Yardim, S Cayci, N He | 3 | 2023 |
Optimal learning for dynamic coding in deadline-constrained multi-channel networks S Cayci, A Eryilmaz IEEE/ACM Transactions on Networking 27 (3), 1043-1054, 2019 | 3 | 2019 |
Fisher-Rao Gradient Flows of Linear Programs and State-Action Natural Policy Gradients J Müller, S Çaycı, G Montúfar arXiv preprint arXiv:2403.19448, 2024 | 2 | 2024 |
Convergence of Gradient Descent for Recurrent Neural Networks: A Nonasymptotic Analysis S Cayci, A Eryilmaz arXiv preprint arXiv:2402.12241, 2024 | 2 | 2024 |