On Expressive Power of Looped Transformers: Theoretical Analysis and Enhancement via Timestep Encoding

Kevin Xu; Issei Sato

2025 ICML ICML 2025

On Expressive Power of Looped Transformers: Theoretical Analysis and Enhancement via Timestep Encoding

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Kevin Xu, Issei Sato

Topics

Machine Learning > Optimization & Theory > Learning Theory Machine Learning > Application Areas > Efficient Computing Deep Learning > Architectures > Transformers

Keywords

approximation rate scaling parameter modulus of continuity looped transformer sequence-to-sequence function timestep encoding

Download PDF