Subgradient Sampling for Nonsmooth Nonconvex Minimization

DOI10.1137/22m1479178arXiv2202.13744OpenAlexW4281661032MaRDI QIDQ6076858

Tam Le, Jérôme Bolte, Edouard Pauwels

Publication date: 17 October 2023

Published in: SIAM Journal on Optimization (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2202.13744

zbMATH Keywords

stochastic gradientpath-differentiabilityconservative gradientonline deep learningsubgradient sampling

Mathematics Subject Classification ID

Analysis of algorithms and problem complexity (68Q25) Graph theory (including graph drawing) in computer science (68R10) Computer graphics; computational geometry (digital and algorithmic aspects) (68U05)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Stability under integration of sums of products of real globally subanalytic functions and their logarithms
• Topological aspects of nonsmooth optimization.
• Uniform laws of large numbers for set-valued mappings and subdifferentials of random functions
• Stochastic generalized gradient method for nonconvex nonsmooth stochastic optimization
• Ergodic properties of weak asymptotic pseudotrajectories for semiflows
• Stochastic heavy ball
• Correction to On the real exponential field with restricted analytic functions
• Geometric categories and o-minimal structures
• Conservative set valued fields, automatic differentiation, stochastic gradient methods and deep learning
• Stochastic generalized gradient methods for training nonconvex nonsmooth neural networks
• Convergence of constant step stochastic gradient descent for non-smooth non-convex functions
• Convergence of a stochastic subgradient method with averaging for nonsmooth nonconvex constrained optimization
• Stochastic subgradient method converges on tame functions
• Conservative and semismooth derivatives are equivalent for semialgebraic maps
• Path differentiability of ODE flows
• Stochastic proximal subgradient descent oscillates in the vicinity of its accumulation set
• Stochastic generalized-differentiable functions in the problem of nonconvex nonsmooth stochastic optimization
• Clarke Subgradients of Stratifiable Functions
• Optimization Methods for Large-Scale Machine Learning
• ERGODIC PROPERTIES OF WEAK ASYMPTOTIC PSEUDOTRAJECTORIES FOR SET-VALUED DYNAMICAL SYSTEMS
• A Stochastic Subgradient Method for Nonsmooth Nonconvex Multilevel Composition Optimization
• An Inertial Newton Algorithm for Deep Learning
• Stochastic Approximations and Differential Inclusions
• Learning representations by back-propagating errors
• A General Chain Rule for Derivatives and the Change of Variables Formula for the Lebesgue Integral
• Probability
• Conservative parametric optimality and the ridge method for tame min-max problems

This page was built for publication: Subgradient Sampling for Nonsmooth Nonconvex Minimization