Accelerated stochastic approximation with state-dependent noise

DOI10.1007/S10107-024-02138-4MaRDI QIDQ6932191zbMATH OpenFDO

Authors Sasila Ilandarideva, Anatoli Juditsky, Guanghui Lan, Tianjiao Li

Publication date 9 September 2025

Published in Mathematical Programming. Series A. Series B (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/S10107-024-02138-4

zbMATH Keywords

accelerated stochastic approximationsparse recoverystate-dependent noisestochastic gradient extrapolationstochastic optimization

Mathematics Subject Classification ID

Generalized linear models (logistic models) (62J12) Stochastic approximation (62L20) Stochastic programming (90C15) Convex programming (90C25)

Cites work

• A Probabilistic and RIPless Theory of Compressed Sensing
• Acceleration of Stochastic Approximation by Averaging
• Accuracy Guarantees for <formula formulatype="inline"> <tex Notation="TeX">$\ell_1$</tex></formula>-Recovery
• An optimal method for stochastic composite optimization
• Between hard and soft thresholding: optimal iterative thresholding algorithms
• Deterministic and stochastic primal-dual subgradient algorithms for uniformly convex minimization
• First-order and stochastic optimization methods for machine learning
• scientific article; zbMATH DE number 3922389 (Why is no real title available?)
• scientific article; zbMATH DE number 3790207 (Why is no real title available?)
• scientific article; zbMATH DE number 3790208 (Why is no real title available?)
• Iterative hard thresholding for compressed sensing
• Multivariate T-Distributions and Their Applications
• Near-ideal model selection by \(\ell _{1}\) minimization
• Nuclear-norm penalization and optimal rates for noisy low-rank matrix completion
• On first-order algorithms for \(\ell_{1}/\)nuclear norm minimization
• Optimal methods of smooth convex minimization
• Optimal Stochastic Approximation Algorithms for Strongly Convex Stochastic Composite Optimization I: A Generic Algorithmic Framework
• Optimal stochastic approximation algorithms for strongly convex stochastic composite optimization. II: Shrinking procedures and optimal algorithms
• Random gradient extrapolation for distributed and stochastic optimization
• Robust Stochastic Approximation Approach to Stochastic Programming
• Simple and optimal methods for stochastic variational inequalities. I: Operator extrapolation
• Simple and optimal methods for stochastic variational inequalities. II: Markovian noise and policy evaluation in reinforcement learning
• Simultaneous analysis of Lasso and Dantzig selector
• Sparse recovery by reduced variance stochastic approximation
• Stable signal recovery from incomplete and inaccurate measurements
• The Dantzig selector: statistical estimation when \(p\) is much larger than \(n\). (With discussions and rejoinder).
• Tight Oracle Inequalities for Low-Rank Matrix Recovery From a Minimal Number of Noisy Random Measurements

This page was built for publication: Accelerated stochastic approximation with state-dependent noise

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6932191)