A Generic Approach for Escaping Saddle points - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2018

A Generic Approach for Escaping Saddle points

Résumé

A central challenge to using first-order methods for optimizing nonconvex problems is the presence of saddle points. First-order methods often get stuck at saddle points, greatly deteriorating their performance. Typically, to escape from saddles one has to use second-order methods. However, most works on second-order methods rely extensively on expensive Hessian-based computations, making them impractical in large-scale settings. To tackle this challenge, we introduce a generic framework that minimizes Hessian based computations while at the same time provably converging to second-order critical points. Our framework carefully alternates between a first-order and a second-order subroutine, using the latter only close to saddle points, and yields convergence results competitive to the state-of-the-art. Empirical results suggest that our strategy also enjoys a good practical performance.

Dates et versions

hal-01652150 , version 1 (30-11-2017)

Identifiants

Citer

Sashank J Reddi, Manzil Zaheer, Suvrit Sra, Barnabas Poczos, Francis Bach, et al.. A Generic Approach for Escaping Saddle points. AISTATS 2018 - 22nd International Conference on Artificial Intelligence and Statistics, Apr 2018, Canary Islands, Spain. ⟨hal-01652150⟩
182 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More