11 citations · 35 across the 20 of their papers we have counts for
23 papers
A Comparative Analysis of Attention versus State-Space Models for In-Context Learning
Enes Arda, Semih Cayci, Atilla Eryilmaz
Transformers and state-space models (SSMs) are two prominent sequential learning architectures, yet their comparison remains largely empirical and existing theoretical analyses are…
Preference-Based Reward Learning under Partial Observability with Inexact Dynamics
Reza Zolnouri, Semih Cayci
In this paper, we study how partial observability and inexact latent-state inference affect reward learning from preferences. To that end, we study preference-based reward learning…
Finite-Time Analysis of Gradient Descent for Shallow Transformers
Enes Arda, Semih Cayci, Atilla Eryilmaz
Understanding why Transformers perform so well remains challenging due to their non-convex optimization landscape. In this work, we analyze a shallow Transformer with independe…
Non-Asymptotic Optimization and Generalization Bounds for Stochastic Gauss-Newton in Overparameterized Models
Semih Cayci
An important question in deep learning is how higher-order optimization methods affect generalization. In this work, we analyze a stochastic Gauss-Newton (SGN) method with Levenber…
Extraction of Moment Closures for Strongly Non-Equilibrium Flows via Machine Learning
Hang Song, Satyvir Singh, Manuel Torrilhon +1
We introduce a machine learning framework for moment-equation modeling of rarefied gas flows, addressing strongly non-equilibrium conditions inaccessible to conventional computatio…
Convergence of Stochastic Gradient Langevin Dynamics in the Lazy Training Regime
Noah Oberweis, Semih Cayci
Continuous-time models provide important insights into the training dynamics of optimization algorithms in deep learning. In this work, we establish a non-asymptotic convergence an…
A Variational Inequality Approach to Independent Learning in Static Mean-Field Games
Batuhan Yardim, Semih Cayci, Niao He
Competitive games involving thousands or even millions of players are prevalent in real-world contexts, such as transportation, communications, and computer networks. However, lear…
A Riemannian Optimization Perspective of the Gauss-Newton Method for Feedforward Neural Networks
Semih Cayci
In this work, we establish non-asymptotic convergence bounds for the Gauss-Newton method in training neural networks with smooth activations. In the underparameterized regime, the…
Optimal Rates of Convergence for Entropy Regularization in Discounted Markov Decision Processes
Johannes Müller, Semih Cayci
We study the error introduced by entropy regularization in infinite-horizon discrete discounted Markov decision processes. We show that this error decreases exponentially in the in…
Recurrent Natural Policy Gradient for POMDPs
Semih Cayci, Atilla Eryilmaz
Solving partially observable Markov decision processes (POMDPs) remains a fundamental challenge in reinforcement learning (RL), primarily due to the curse of dimensionality induced…
Fisher-Rao Gradient Flows of Linear Programs and State-Action Natural Policy Gradients
Johannes Müller, Semih Çaycı, Guido Montúfar
Kakade's natural policy gradient method has been studied extensively in recent years, showing linear convergence with and without regularization. We study another natural gradient…
Convergence of Gradient Descent for Recurrent Neural Networks: A Nonasymptotic Analysis
Semih Cayci, Atilla Eryilmaz
We analyze recurrent neural networks with diagonal hidden-to-hidden weight matrices, trained with gradient descent in the supervised learning setting, and prove that gradient desce…
Provably Robust Temporal Difference Learning for Heavy-Tailed Rewards
Semih Cayci, Atilla Eryilmaz
In a broad class of reinforcement learning applications, stochastic rewards have heavy-tailed distributions, which lead to infinite second-order moments for stochastic (semi)gradie…
Policy Mirror Ascent for Efficient and Independent Learning in Mean Field Games
Batuhan Yardim, Semih Cayci, Matthieu Geist +1
Mean-field games have been used as a theoretical tool to obtain an approximate Nash equilibrium for symmetric and anonymous -player games. However, limiting applicability, exist…
Finite-Time Analysis of Entropy-Regularized Neural Natural Actor-Critic Algorithm
Semih Cayci, Niao He, R. Srikant
Natural actor-critic (NAC) and its variants, equipped with the representation power of neural networks, have demonstrated impressive empirical success in solving Markov decision pr…
Finite-Time Analysis of Natural Actor-Critic for POMDPs
Semih Cayci, Niao He, R. Srikant
We consider the reinforcement learning problem for partially observed Markov decision processes (POMDPs) with large or even countably infinite state spaces, where the controller ha…
A Lyapunov-Based Methodology for Constrained Optimization with Bandit Feedback
Semih Cayci, Yilin Zheng, Atilla Eryilmaz
In a wide variety of applications including online advertising, contractual hiring, and wireless scheduling, the controller is constrained by a stringent budget constraint on the a…
Linear Convergence of Entropy-Regularized Natural Policy Gradient with Linear Function Approximation
Semih Cayci, Niao He, R. Srikant
Natural policy gradient (NPG) methods with entropy regularization achieve impressive empirical success in reinforcement learning problems with large state-action spaces. However, t…
Sample Complexity and Overparameterization Bounds for Temporal Difference Learning with Neural Network Approximation
Semih Cayci, Siddhartha Satpathi, Niao He +1
In this paper, we study the dynamics of temporal difference learning with neural network-based value function approximation over a general state space, namely, \emph{Neural TD lear…
Group-Fair Online Allocation in Continuous Time
Semih Cayci, Swati Gupta, Atilla Eryilmaz
The theory of discrete-time online learning has been successfully applied in many problems that involve sequential decision-making under uncertainty. However, in many applications…
Continuous-Time Multi-Armed Bandits with Controlled Restarts
Semih Cayci, Atilla Eryilmaz, R. Srikant
Time-constrained decision processes have been ubiquitous in many fundamental applications in physics, biology and computer science. Recently, restart strategies have gained signifi…
Budget-Constrained Bandits over General Cost and Reward Distributions
Semih Cayci, Atilla Eryilmaz, R. Srikant
We consider a budget-constrained bandit problem where each arm pull incurs a random cost, and yields a random reward in return. The objective is to maximize the total expected rewa…
Optimal Learning for Dynamic Coding in Deadline-Constrained Multi-Channel Networks
Semih Cayci, Atilla Eryilmaz
We study the problem of serving randomly arriving and delay-sensitive traffic over a multi-channel communication system with time-varying channel states and unknown statistics. Thi…