5 papers
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…
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…
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…
A Rate-Distortion Framework for Summarization
Enes Arda, Aylin Yener
This paper introduces an information-theoretic framework for text summarization. We define the summarizer rate-distortion function and show that it provides a fundamental lower bou…
Semantic Forwarding for Next Generation Relay Networks
Enes Arda, Emrecan Kutay, Aylin Yener
We consider cooperative semantic text communications facilitated by a relay node. We propose two types of semantic forwarding: semantic lossy forwarding (SLF) and semantic predict-…