Stochastic proximal linear method for structured non-convex problems

DOI10.1080/10556788.2020.1754413zbMath1464.90066OpenAlexW3022734915MaRDI QIDQ5858986

Sergey Voldman, Tamir Hazan, Shoham Sabach

Publication date: 15 April 2021

Published in: Optimization Methods and Software (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1080/10556788.2020.1754413

zbMATH Keywords

convergence analysisstochasticproximal-gradient algorithmsnon-convex non-smooth minimization

Mathematics Subject Classification ID

Numerical mathematical programming methods (65K05) Nonconvex programming, global optimization (90C26) Convex functions and convex programs in convex geometry (52A41) Decomposition methods (49M27) Convexity of real functions of several variables, generalizations (26B25)

Uses Software

• Pegasos
• AdaGrad
• Adam
• CNN-RNN
• Saga

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• A proximal method for composite minimization
• Minimizing finite sums with the stochastic average gradient
• Pegasos: primal estimated sub-gradient solver for SVM
• A simplified view of first order methods for optimization
• A fast dual proximal gradient algorithm for convex minimization and applications
• The value function approach to convergence analysis in composite optimization
• An extended sequential quadratically constrained quadratic programming algorithm for nonlinear, semidefinite, and second-order cone programming
• Majorization-Minimization Procedures and Convergence of SQP Methods for Semi-Algebraic and Tame Programs
• Variational Analysis
• Accelerated Methods for NonConvex Optimization
• Optimization Methods for Large-Scale Machine Learning
• Finding approximate local minima faster than gradient descent
• A Stochastic Approximation Method

This page was built for publication: Stochastic proximal linear method for structured non-convex problems