Escaping saddle points without Lipschitz smoothness: the power of nonlinear preconditioning

NeurIPSSpotlight2025

Authors: Alexander Bodard, Panagiotis Patrinos
Venue: NeurIPS 2025
Track: Spotlight

TL;DR

We study generalized smoothness in nonconvex optimization, focusing on $(L_0, L_1)$-smoothness and anisotropic smoothness…

Opening excerpt from the authors’ abstract. source

Read the paper

OpenReview

Topics

optimization

← All NeurIPS 2025 Spotlight papers · Browse the whole archive