Unified analysis of stochastic gradient methods for composite convex and smooth optimization

DOI10.1007/s10957-023-02297-yarXiv2006.11573OpenAlexW3036623140MaRDI QIDQ6086133

Peter Richtárik, Othmane Sebbouh, Nicolas Loizou, Ahmed Khaled, Robert M. Gower

Publication date: 9 November 2023

Published in: Journal of Optimization Theory and Applications (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2006.11573

zbMATH Keywords

stochastic optimizationconvex optimizationvariance reductioncomposite optimization

Mathematics Subject Classification ID

Convex programming (90C25) Stochastic programming (90C15)

Cites Work

• Unnamed Item
• Minimizing finite sums with the stochastic average gradient
• High-dimensional Ising model selection using \(\ell _{1}\)-regularized logistic regression
• Stochastic quasi-gradient methods: variance reduction via Jacobian sketching
• Coordinate descent algorithms
• Efficiency of Coordinate Descent Methods on Huge-Scale Optimization Problems
• Robust Stochastic Approximation Approach to Stochastic Programming
• First-Order Methods in Optimization
• Katyusha: the first direct acceleration of stochastic gradient methods
• Convergence Rates for Deterministic and Stochastic Subgradient Methods without Lipschitz Continuity
• Regularization and Variable Selection Via the Elastic Net
• On perturbed proximal gradient algorithms
• Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming
• Understanding Machine Learning
• A Stochastic Approximation Method
• Stochastic distributed learning with gradient quantization and double-variance reduction
• Stochastic gradient descent, weighted sampling, and the randomized Kaczmarz algorithm

This page was built for publication: Unified analysis of stochastic gradient methods for composite convex and smooth optimization