Algorithms of robust stochastic optimization based on mirror descent method

DOI10.1134/S0005117919090042zbMath1431.93064arXiv1907.02707OpenAlexW2972939971WikidataQ127239858 ScholiaQ127239858MaRDI QIDQ2289049

Alexandre B. Tsybakov, Alexander Nazin, Anatoli B. Juditsky, Arkadi Nemirovski

Publication date: 28 January 2020

Published in: Automation and Remote Control (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1907.02707

zbMATH Keywords

stochastic optimization algorithmsmirror descent methodrobust confidence setsconvex composite stochastic optimizationrobust iterative algorithms

Mathematics Subject Classification ID

Sensitivity (robustness) (93B35) Optimal stochastic control (93E20)

Related Items (7)

Optimal robust mean and location estimation via convex programs with respect to any pseudo-norms ⋮ Gradient-free methods for non-smooth convex stochastic optimization with heavy-tailed noise on convex compact ⋮ Unnamed Item ⋮ Nonlinear Gradient Mappings and Stochastic Optimization: A General Framework with Applications to Heavy-Tail Noise ⋮ Algorithms with gradient clipping for stochastic optimization with heavy-tailed noise ⋮ ERM and RERM are optimal estimators for regression problems when malicious outliers corrupt the labels ⋮ Unnamed Item

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Geometric median and robust estimation in Banach spaces
• An optimal method for stochastic composite optimization
• Sub-Gaussian mean estimators
• Robust linear least squares regression
• Analysis of robust stochastic approximation algorithms for process identification
• Convergence and robustness of the Robbins-Monro algorithm truncated at randomly varying bounds
• Adaptive estimation algorithms (convergence, optimality, stability)
• Robust identification
• Robust pseudogradient adaptation algorithms
• On tail probabilities for martingales
• Sub-Gaussian estimators of the mean of a random vector
• Challenging the empirical mean and empirical variance: a deviation study
• Online estimation of the geometric median in Hilbert spaces: nonasymptotic confidence balls
• Robust classification via MOM minimization
• Risk minimization by median-of-means tournaments
• Deterministic and stochastic primal-dual subgradient algorithms for uniformly convex minimization
• Convergence Analysis of a Proximal-Like Minimization Algorithm Using Bregman Functions
• Stochastic Approximation for Multivariate and Functional Median
• Robust Stochastic Approximation Approach to Stochastic Programming
• Robust estimation using the Robbins-Monro stochastic approximation algorithm
• Optimal and robust kernel algorithms for passive stochastic approximation
• Robust estimation via stochastic approximation
• Robustness analysis for stochastic approximation algorithms
• Optimal Stochastic Approximation Algorithms for Strongly Convex Stochastic Composite Optimization I: A Generic Algorithmic Framework
• Accuracy Guarantees for <formula formulatype="inline"> <tex Notation="TeX">$\ell_1$</tex></formula>-Recovery
• Bandits With Heavy Tail
• Robust Estimation of a Location Parameter
• The 1972 Wald Lecture Robust Statistics: A Review
• Robust Statistics

This page was built for publication: Algorithms of robust stochastic optimization based on mirror descent method