Stochastic Methods for Composite and Weakly Convex Optimization Problems

DOI10.1137/17M1135086OpenAlexW2602608495WikidataQ128861220 ScholiaQ128861220MaRDI QIDQ4561227

John C. Duchi, Feng Ruan

Publication date: 5 December 2018

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

Full work available at URL: https://arxiv.org/abs/1703.08570

zbMATH Keywords

stochastic optimizationdifferential inclusioncomposite optimization

Mathematics Subject Classification ID

Numerical optimization and variational techniques (65K10)

Related Items (31)

Proximal methods avoid active strict saddles of weakly convex functions ⋮ A stochastic subgradient method for distributionally robust non-convex and non-smooth learning ⋮ Stochastic Multilevel Composition Optimization Algorithms with Level-Independent Convergence Rates ⋮ Graphical Convergence of Subgradients in Nonconvex Optimization and Learning ⋮ Coupled Learning Enabled Stochastic Programming with Endogenous Uncertainty ⋮ Stochastic proximal subgradient descent oscillates in the vicinity of its accumulation set ⋮ Learning with risks based on M-location ⋮ Unnamed Item ⋮ Pathological Subgradient Dynamics ⋮ Consistent approximations in composite optimization ⋮ First-order methods for convex optimization ⋮ Convergence of a stochastic subgradient method with averaging for nonsmooth nonconvex constrained optimization ⋮ An Accelerated Inexact Proximal Point Method for Solving Nonconvex-Concave Min-Max Problems ⋮ An algorithm for the minimization of nonsmooth nonconvex functions using inexact evaluations and its worst-case complexity ⋮ Stochastic proximal gradient methods for nonconvex problems in Hilbert spaces ⋮ Stochastic subgradient method converges on tame functions ⋮ Characterization of solutions of strong-weak convex programming problems ⋮ Strong Metric (Sub)regularity of Karush–Kuhn–Tucker Mappings for Piecewise Linear-Quadratic Convex-Composite Optimization and the Quadratic Convergence of Newton’s Method ⋮ A zeroth order method for stochastic weakly convex optimization ⋮ Proximally Guided Stochastic Subgradient Method for Nonsmooth, Nonconvex Problems ⋮ Low-rank matrix recovery with composite optimization: good conditioning and rapid convergence ⋮ Stochastic (Approximate) Proximal Point Methods: Convergence, Optimality, and Adaptivity ⋮ An Inertial Newton Algorithm for Deep Learning ⋮ A Stochastic Subgradient Method for Nonsmooth Nonconvex Multilevel Composition Optimization ⋮ Efficiency of minimizing compositions of convex functions and smooth maps ⋮ Stochastic variance-reduced prox-linear algorithms for nonconvex composite optimization ⋮ On the Convergence of Mirror Descent beyond Stochastic Convex Programming ⋮ Computation for latent variable model estimation: a unified stochastic proximal framework ⋮ Stochastic Difference-of-Convex-Functions Algorithms for Nonconvex Programming ⋮ Sufficient conditions for a minimum of a strongly quasiconvex function on a weakly convex set ⋮ A Study of Convex Convex-Composite Functions via Infimal Convolution with Applications

Uses Software

• AdaGrad
• Convex.jl
• PhaseLift
• Wirtinger Flow

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Stochastic compositional gradient descent: algorithms for minimizing compositions of expected-value functions
• Solution of nonconvex nonsmooth stochastic optimization problems
• Stochastic generalized gradient method for nonconvex nonsmooth stochastic optimization
• Introductory lectures on convex optimization. A basic course.
• Non-smooth dynamical systems
• Measurable dependence of convex sets and functions on parameters
• Stochastic optimization problems with nondifferentiable cost functionals
• A function not constant on a connected set of critical points
• PhaseLift: Exact and Stable Signal Recovery from Magnitude Measurements via Convex Programming
• Phase Retrieval via Wirtinger Flow: Theory and Algorithms
• A Linearization Method for Nonsmooth Stochastic Programming Problems
• Clarke Subgradients of Stratifiable Functions
• Critical values of set-valued maps with stratifiable graphs. Extensions of Sard and Smale-Sard theorems
• Characterizations of Łojasiewicz inequalities: Subgradient flows, talweg, convexity
• Robust Stochastic Approximation Approach to Stochastic Programming
• Descent methods for composite nondifferentiable optimization problems
• On some properties of the generalized gradient method
• First and second order conditions for a class of nondifferentiable optimization problems
• A model algorithm for composite nondifferentiable optimization problems
• Monotone Operators and the Proximal Point Algorithm
• Analysis of recursive stochastic algorithms
• Variational Analysis
• Trust Region Methods
• A variational perspective on accelerated methods in optimization
• Prox-regular functions in variational analysis
• Variational Analysis of Regular Mappings
• Error Bounds, Quadratic Growth, and Linear Convergence of Proximal Methods
• Stochastic Approximations and Differential Inclusions

This page was built for publication: Stochastic Methods for Composite and Weakly Convex Optimization Problems