Dimension-adapted Momentum Outscales SGD

NeurIPSSpotlight2025

Authors: Damien Ferbach, Katie Everett, Gauthier Gidel, Elliot Paquette, Courtney Paquette
Venue: NeurIPS 2025
Track: Spotlight

TL;DR

We investigate scaling laws for stochastic momentum algorithms on the power law random features model, parameterized by data complexity, target complexity, and model size…

Opening excerpt from the authors’ abstract. source

Read the paper

OpenReview

Topics

scaling law

← All NeurIPS 2025 Spotlight papers · Browse the whole archive