most citedSubmodular Maximization Approaches for Equitable Client Selection in Federated Learning

2 citations · 2 across the 4 of their papers we have counts for

collaborators
Showing cs.LGShow all

9 papers · 1 filter

cs.LG2026

EGGROLL, Unrolled: Understanding and Improving Low-Rank Evolution Strategies at Scale

Ege C. Kaya, Abolfazl Hashemi

EGGROLL makes evolution strategies (ES) practical for LLMs by replacing dense Gaussian weight perturbations with low-rank Gaussian products, often of rank one. This choice is compu…

cs.LG2026

Learning to Control Coupled-Dynamics Environments with Joint Markov Decision Processes

Ege C. Kaya, Aliasghar Pourghani, Mahsa Ghasemi +2

Coupled-dynamics environments expose the one-step outcomes that would follow from several possible counterfactual actions under a common realization of exogenous randomness. The or…

cs.LG2026

A Banach-Space Theory of Markovian Halpern Iteration for Non-Expansive Maps

Ege C. Kaya, Arda Fazla, M. Berk Sahin +1

We study stochastic approximation of fixed points of a non-expansive operator when the oracle samples originate from a continuing Markovian trajectory. A direct block-minibatch imp…

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-…