Learning Linear Attention in Polynomial Time

NeurIPSOral2025

Authors: Morris Yau, Ekin Akyürek, Jiayuan Mao, Joshua B. Tenenbaum, Stefanie Jegelka, Jacob Andreas
Affiliation: Massachusetts Institute of Technology
Venue: NeurIPS 2025
Track: Oral

TL;DR

We develop algorithms that are guaranteed to PAC learn transformers.

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

transformer attention

← All NeurIPS 2025 Oral papers · Browse the whole archive