Skip to content
conftrace_
2025 ICML ICML 2025

Positional Attention: Expressivity and Learnability of Algorithmic Computation

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

Artur Back de Luca, George Giapitzakis, Shenghao Yang, Petar Veličković, Kimon Fountoulakis

Topics

Machine Learning > Optimization & Theory > Learning Theory Machine Learning > Optimization & Theory > Theory Deep Learning > Architectures > Transformers

Keywords

sample complexity transformer expressivity positional attention algorithmic execution parallel computational models
Download PDF