Faster perturbed stochastic gradient methods for finding local minima

MaRDI QIDQ7028782zbMATH OpenFDO

Authors Zixiang Chen, Dongruo Zhou, Quanquan Gu

Publication date 11 February 2025

Full work available at URL https://proceedings.mlr.press/v167/chen22b.html

zbMATH Keywords

local minimanonconvex optimizationstochastic gradient descent

Mathematics Subject Classification ID

Analysis of algorithms and problem complexity (68Q25) Learning and adaptive systems in artificial intelligence (68T05) Stochastic programming (90C15) Nonconvex programming, global optimization (90C26)

Cites work

• A proximal stochastic gradient method with progressive variance reduction
• Accelerated methods for nonconvex optimization
• Cubic regularization of Newton method and its global performance
• Finding approximate local minima faster than gradient descent
• scientific article; zbMATH DE number 7255141 (Why is no real title available?)
• Most tensor problems are NP-hard
• Optimum bounds for the distributions of martingales in Banach spaces
• Some dimension-free features of vector-valued martingales

Cited in

(1)

• On the convergence of SignSGD under weak first- and second-order gradient Lipschitz

This page was built for publication: Faster perturbed stochastic gradient methods for finding local minima

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7028782)