A Variable Sample-Size Stochastic Quasi-Newton Method for Smooth and Nonsmooth Stochastic Convex Optimization

DOI10.1287/MOOR.2021.1147zbMath1492.90104arXiv1804.05368OpenAlexW2797791799MaRDI QIDQ5076721

Farzad Yousefian, Afrooz Jalilzadeh, Angelia Nedić, Uday V. Shanbhag

Publication date: 17 May 2022

Published in: Mathematics of Operations Research (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1804.05368

zbMATH Keywords

stochastic optimizationconvex optimizationquasi-Newton methods

Mathematics Subject Classification ID

Convex programming (90C25) Stochastic programming (90C15) Methods of quasi-Newton type (90C53)

Related Items (2)

An overview of stochastic quasi-Newton methods for large-scale machine learning ⋮ An inexact restoration-nonsmooth algorithm with variable accuracy for stochastic nonsmooth convex optimization problems in machine learning and stochastic linear complementarity problems

Uses Software

• L-BFGS
• RCV1
• ASTRO-DF

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A Stochastic Quasi-Newton Method for Large-Scale Optimization
• Accelerated gradient methods for nonconvex nonlinear and stochastic programming
• Sample size selection in optimization methods for machine learning
• On the limited memory BFGS method for large scale optimization
• Variable-number sample-path optimization
• Global convergence rate analysis of unconstrained optimization methods based on probabilistic models
• On smoothing, regularization, and averaging in stochastic approximation methods for stochastic variational inequality problems
• On variance reduction for stochastic smooth convex optimization with multiplicative noise
• Globally convergent variable metric method for convex nonsmooth unconstrained minimization
• Gradient trust region algorithm with limited memory BFGS update for nonsmooth convex minimization
• The Sample Average Approximation Method for Stochastic Discrete Optimization
• Global Convergence of Online Limited Memory BFGS
• Strongly Convex Functions, Moreau Envelopes, and the Generic Nature of Convex Functions with Strong Minimizers
• A Quasi-Newton Approach to Nonsmooth Convex Optimization Problems in Machine Learning
• Hybrid Deterministic-Stochastic Methods for Data Fitting
• Smoothing and First Order Methods: A Unified Framework
• On Choosing Parameters in Retrospective-Approximation Algorithms for Stochastic Root Finding and Simulation Optimization
• Robust Stochastic Approximation Approach to Stochastic Programming
• ASTRO-DF: A Class of Adaptive Sampling Trust-Region Algorithms for Derivative-Free Stochastic Optimization
• Adaptive Sampling Strategies for Stochastic Optimization
• Variable-sample methods for stochastic optimization
• RES: Regularized Stochastic BFGS Algorithm
• First-Order Methods in Optimization
• On Sampling Rates in Simulation-Based Recursions
• Variance-Based Extragradient Methods with Line Search for Stochastic Variational Inequalities
• On Stochastic and Deterministic Quasi-Newton Methods for Nonstrongly Convex Optimization: Asymptotic Convergence and Rate Analysis
• A Stochastic Line Search Method with Expected Complexity Analysis
• A Proximal Stochastic Gradient Method with Progressive Variance Reduction
• New limited memory bundle method for large-scale nonsmooth optimization
• Proximité et dualité dans un espace hilbertien
• Stochastic Quasi-Newton Methods for Nonconvex Stochastic Optimization
• A Stochastic Approximation Method

This page was built for publication: A Variable Sample-Size Stochastic Quasi-Newton Method for Smooth and Nonsmooth Stochastic Convex Optimization