On the Surprising Effectiveness of Large Learning Rates under Standard Width Scaling

NeurIPSSpotlight2025

Authors
Moritz Haas, Sebastian Bordt, Ulrike von Luxburg, Leena Chennuru Vankadara
Venue
NeurIPS 2025
Track
Spotlight

TL;DR

Scaling limits, such as infinite-width limits, serve as promising theoretical tools to study large-scale models…

Opening excerpt from the authors’ abstract. source

Read the paper

Related NeurIPS papers

← All NeurIPS 2025 Spotlight papers · Browse the whole archive