Semih Cayci

44 papers A* 4A 1B 3Journal 32Unranked 4
YearRankTypeTitle / Venue / Authors
2026 J jnl
Convergence of Stochastic Gradient Langevin Dynamics in the Lazy Training Regime.
Trans. Mach. Learn. Res.
Noah Oberweis, Semih Cayci
2026 J jnl
Finite-Time Analysis of Gradient Descent for Shallow Transformers.
CoRR
Enes Arda, Semih Cayci, Atilla Eryilmaz
2025 J jnl
A Variational Inequality Approach to Independent Learning in Static Mean-Field Games.
CoRR
Batuhan Yardim, Semih Cayci, Niao He
2025 J jnl
Budgeted-Bandits with Controlled Restarts with Applications in Learning and Computing.
Trans. Mach. Learn. Res.
Semih Cayci, Yilin Zheng, Atilla Eryilmaz
2025 J jnl
Convergence of Gradient Descent for Recurrent Neural Networks: A Nonasymptotic Analysis.
SIAM J. Math. Data Sci.
Semih Cayci, Atilla Eryilmaz
2025 J jnl
Convergence of Stochastic Gradient Langevin Dynamics in the Lazy Training Regime.
CoRR
Noah Oberweis, Semih Cayci
2025 J jnl
Fisher-Rao Gradient Flows of Linear Programs and State-Action Natural Policy Gradients.
SIAM J. Optim.
Johannes Müller, Semih Cayci, Guido Montúfar
2025 J jnl
Non-Asymptotic Optimization and Generalization Bounds for Stochastic Gauss-Newton in Overparameterized Models.
CoRR
Semih Cayci
2025 J jnl
Recurrent Natural Policy Gradient for POMDPs.
Trans. Mach. Learn. Res.
Semih Cayci, Atilla Eryilmaz
2024 J jnl
Convergence of Entropy-Regularized Natural Policy Gradient with Linear Function Approximation.
SIAM J. Optim.
Semih Cayci, Niao He, R. Srikant
2024 J jnl
Convergence of Gradient Descent for Recurrent Neural Networks: A Nonasymptotic Analysis.
CoRR
Semih Cayci, Atilla Eryilmaz
2024 J jnl
Essentially Sharp Estimates on the Entropy Regularization Error in Discrete Discounted Markov Decision Processes.
CoRR
Johannes Müller, Semih Cayci
2024 J jnl
Fast Online Learning of Vulnerabilities for Networks With Propagating Failures.
IEEE/ACM Trans. Netw.
Yilin Zheng, Semih Cayci, Atilla Eryilmaz
2024 J jnl
Finite-Time Analysis of Entropy-Regularized Neural Natural Actor-Critic Algorithm.
Trans. Mach. Learn. Res.
Semih Cayci, Niao He, R. Srikant
2024 J jnl
Finite-Time Analysis of Natural Actor-Critic for POMDPs.
SIAM J. Math. Data Sci.
Semih Cayci, Niao He, R. Srikant
2024 J jnl
Fisher-Rao Gradient Flows of Linear Programs and State-Action Natural Policy Gradients.
CoRR
Johannes Müller, Semih Cayci, Guido Montúfar
2024 J jnl
Gauss-Newton Dynamics for Neural Networks: A Riemannian Optimization Perspective.
CoRR
Semih Cayci
2024 J jnl
Recurrent Natural Policy Gradient for POMDPs.
CoRR
Semih Cayci, Atilla Eryilmaz
2023 A* conf
Policy Mirror Ascent for Efficient and Independent Learning in Mean Field Games.
ICML
Batuhan Yardim, Semih Cayci, Matthieu Geist, Niao He
2023 A* conf
Provably Robust Temporal Difference Learning for Heavy-Tailed Rewards.
NeurIPS
Semih Cayci, Atilla Eryilmaz
2023 J jnl
Provably Robust Temporal Difference Learning for Heavy-Tailed Rewards.
CoRR
Semih Cayci, Atilla Eryilmaz
2023 J jnl
Sample Complexity and Overparameterization Bounds for Temporal-Difference Learning With Neural Network Approximation.
IEEE Trans. Autom. Control.
Semih Cayci, Siddhartha Satpathi, Niao He, R. Srikant
2022 A* conf
A Lyapunov-Based Methodology for Constrained Optimization with Bandit Feedback.
AAAI
Semih Cayci, Yilin Zheng, Atilla Eryilmaz
2022 J jnl
Finite-Time Analysis of Entropy-Regularized Neural Natural Actor-Critic Algorithm.
CoRR
Semih Cayci, Niao He, R. Srikant
2022 J jnl
Learning to Control Partially Observed Systems with Finite Memory.
CoRR
Semih Cayci, Niao He, R. Srikant
2022 J jnl
Policy Mirror Ascent for Efficient and Independent Learning in Mean Field Games.
CoRR
Batuhan Yardim, Semih Cayci, Matthieu Geist, Niao He
2021 J jnl
A Lyapunov-Based Methodology for Constrained Optimization with Bandit Feedback.
CoRR
Semih Cayci, Yilin Zheng, Atilla Eryilmaz
2021 J jnl
Linear Convergence of Entropy-Regularized Natural Policy Gradient with Linear Function Approximation.
CoRR
Semih Cayci, Niao He, R. Srikant
2021 J jnl
Sample Complexity and Overparameterization Bounds for Projection-Free Neural TD Learning.
CoRR
Semih Cayci, Siddhartha Satpathi, Niao He, R. Srikant
2020 A conf
Budget-Constrained Bandits over General Cost and Reward Distributions.
AISTATS
Semih Cayci, Atilla Eryilmaz, R. Srikant
2020 J jnl
Budget-Constrained Bandits over General Cost and Reward Distributions.
CoRR
Semih Cayci, Atilla Eryilmaz, R. Srikant
2020 J jnl
Continuous-Time Multi-Armed Bandits with Controlled Restarts.
CoRR
Semih Cayci, Atilla Eryilmaz, R. Srikant
2020 A* conf
Group-Fair Online Allocation in Continuous Time.
NeurIPS
Semih Cayci, Swati Gupta, Atilla Eryilmaz
2020 J jnl
Group-Fair Online Allocation in Continuous Time.
CoRR
Semih Cayci, Swati Gupta, Atilla Eryilmaz
2019 — conf
Hardware-Efficient Quantized Polar Decoding with Optimized Lookup Table.
OECC/PSC
Toshiaki Koike-Akino, Ye Wang, Semih Cayci, David S. Millar, Keisuke Kojima, Kieran Parsons
2019 — conf
Learning to Control Renewal Processes with Bandit Feedback.
SIGMETRICS (Abstracts)
Semih Cayci, Atilla Eryilmaz, Rayadurgam Srikant
2019 J jnl
Learning to Control Renewal Processes with Bandit Feedback.
Proc. ACM Meas. Anal. Comput. Syst.
Semih Cayci, Atilla Eryilmaz, R. Srikant
2019 — conf
Nonbinary Polar Coding for Multilevel Modulation.
OFC
Semih Cayci, Toshiaki Koike-Akino, Ye Wang
2019 J jnl
Optimal Learning for Dynamic Coding in Deadline-Constrained Multi-Channel Networks.
IEEE/ACM Trans. Netw.
Semih Cayci, Atilla Eryilmaz
2018 J jnl
Optimal Learning for Dynamic Coding in Deadline-Constrained Multi-Channel Networks.
CoRR
Semih Cayci, Atilla Eryilmaz
2017 B conf
Learning for serving deadline-constrained traffic in multi-channel wireless networks.
WiOpt
Semih Cayci, Atilla Eryilmaz
2016 B conf
On the Multi-Channel Capacity Gains of Millimeter-Wave Communication.
GLOBECOM
Semih Cayci, Atilla Eryilmaz
2013 B conf
Lossless polar compression of g-ary sources.
ISIT
Semih Cayci, Orhan Arikan
2012 — conf
Polar code construction for non-binary source alphabets.
SIU
Semih Cayci, Orhan Arikan, Erdal Arikan