Showing 2026Show all
3 papers · 1 filter
cs.LG2026
Sharp Convergence and Sample Complexity of Policy Mirror Descent for Average-Reward MDPs
Enes Arda, Atilla Eryilmaz
Policy mirror descent (PMD) has a mature finite-time theory in discounted Markov decision processes (MDPs), but less is known in the average-reward setting, a more natural objectiv…
cs.LG2026
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…
cs.LG2026
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…