2 papers
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…
cs.IT2025
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…