collaborators

6 papers

cs.LG2026

Quotient-Categorical Representations for Bellman-Compatible Average-Reward Distributional Reinforcement Learning

Ege C. Kaya, Aliasghar Pourghani, Vijay Gupta +1

Average-reward reinforcement learning requires estimating the gain and the bias, which is defined only up to an additive constant. This makes direct distributional analogues ill-po…

cs.LG2026

A Finite-Iteration Theory for Asynchronous Categorical Distributional Temporal-Difference Learning

Ege C. Kaya, Abolfazl Hashemi

We study finite-iteration behavior of the exact asynchronous recursions used by categorical distributional temporal-difference methods. The analysis covers scalar categorical TD in…

cs.LG2026

Lower Bounds and Proximally Anchored SGD for Non-Convex Minimization Under Unbounded Variance

Arda Fazla, Ege C. Kaya, Antesh Upadhyay +1

Analysis of Stochastic Gradient Descent (SGD) and its variants typically relies on the assumption of uniformly bounded variance, a condition that frequently fails in practical non-…

cs.LG2026

Joint MDPs and Reinforcement Learning in Coupled-Dynamics Environments

Ege C. Kaya, Mahsa Ghasemi, Abolfazl Hashemi

Many distributional quantities in reinforcement learning are intrinsically joint across actions, including distributions of gaps and probabilities of superiority. However, the clas…

math.OC2026

Randomized Greedy Methods for Weak Submodular Sensor Selection with Robustness Considerations

Ege C. Kaya, Michael Hibbard, Takashi Tanaka +2

We study a pair of budget- and performance-constrained weak-submodular maximization problems. For computational efficiency, we explore the use of stochastic greedy algorithms which…

cs.LG2026

Localized Distributional Robustness in Submodular Multi-Task Subset Selection

Ege C. Kaya, Abolfazl Hashemi

In this work, we treat the problem of multi-task submodular optimization from the perspective of local distributional robustness within the neighborhood of a reference distribution…