Stochastic online optimization. Single-point and multi-point non-linear multi-armed bandits. Convex and strongly-convex case

DOI10.1134/S0005117917020035zbMATH Open1362.93165MaRDI QIDQ2397263FDOQ2397263

Authors: Alexander V. Gasnikov, E. A. Krymova, A. A. Lagunovskaya, I. N. Usmanova, F. A. Fedorenko 

Publication date: 22 May 2017

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

Recommendations

• Online bandit convex optimisation with stochastic constraints via two-point feedback
• Online convex optimization in the bandit setting: gradient descent without a gradient
• Advances in Computer Science - ASIAN 2004. Higher-Level Decision Making
• Online Convex Optimization With Time-Varying Constraints and Bandit Feedback
• Stochastic convex optimization with bandit feedback
• An Online Learning Approach to a Multi-player N-armed Functional Bandit
• Multi-Armed Bandits: Theory and Applications to Online Learning in Networks
• Bandit convex optimization in non-stationary environments
• Online Successive Convex Approximation for Two-Stage Stochastic Nonconvex Optimization
• Online learning and online convex optimization

zbMATH Keywords

online optimizationstochastic optimizationinexact oraclegradient-free

Mathematics Subject Classification ID

Stochastic programming (90C15) Discrete-time control/observation systems (93C55) Optimal stochastic control (93E20)

Cites Work

• Prediction, Learning, and Games
• Primal-dual subgradient methods for convex problems
• Lectures on modern convex optimization. Analysis, algorithms, and engineering applications
• The concentration of measure phenomenon
• Online convex optimization in the bandit setting: gradient descent without a gradient
• Online learning and online convex optimization
• Regret analysis of stochastic and nonstochastic multi-armed bandit problems
• Title not available (Why is that?)
• Gradient-free proximal methods with inexact oracle for convex stochastic nonsmooth optimization problems on the simplex
• Information-Theoretic Lower Bounds on the Oracle Complexity of Stochastic Convex Optimization
• Optimal Rates for Zero-Order Convex Optimization: The Power of Two Function Evaluations
• On martingale extensions of Vapnik-Chervonenkis theory with applications to online learning

Cited In (31)

• Noisy zeroth-order optimization for non-smooth saddle point problems
• Primal-dual mirror descent method for constraint stochastic optimization problems
• Accelerated directional search with non-Euclidean prox-structure
• Interior-Point Methods for Full-Information and Bandit Online Learning
• Gradient-free two-point methods for solving stochastic nonsmooth convex optimization problems with small non-random noises
• One-point gradient-free methods for smooth and non-smooth saddle-point problems
• Small errors in random zeroth-order optimization are imaginary
• Stochastic adversarial noise in the ``black box optimization problem
• Improved exploitation of higher order smoothness in derivative-free optimization
• Gradient-free federated learning methods with \(l_1\) and \(l_2\)-randomization for non-smooth convex stochastic optimization problems
• Online sequential optimization with biased gradients: theory and applications to censored demand
• On the convergence of gradient-like flows with noisy gradient input
• Non-smooth setting of stochastic decentralized convex optimization problem over time-varying graphs
• Online bandit convex optimisation with stochastic constraints via two-point feedback
• Stochastic zeroth-order discretizations of Langevin diffusions for Bayesian inference
• An accelerated method for derivative-free smooth stochastic convex optimization
• An accelerated directional derivative method for smooth stochastic convex optimization
• Analogues of switching subgradient schemes for relatively Lipschitz-continuous convex programming problems
• Unifying framework for accelerated randomized methods in convex optimization
• Gradient-Free Methods with Inexact Oracle for Convex-Concave Stochastic Saddle-Point Problem
• Beyond the regret minimization barrier: optimal algorithms for stochastic strongly-convex optimization
• A new one-point residual-feedback oracle for black-box learning and control
• Thompson sampling guided stochastic searching on the line for deceptive environments with applications to root-finding problems
• Technical note: Nonstationary stochastic optimization under \(L_{p,q} \)-variation measures
• Stochastic convex optimization with bandit feedback
• Zeroth-order nonconvex stochastic optimization: handling constraints, high dimensionality, and saddle points
• Gradient-free proximal methods with inexact oracle for convex stochastic nonsmooth optimization problems on the simplex
• Gradient-free methods for non-smooth convex stochastic optimization with heavy-tailed noise on convex compact
• On the efficiency of a randomized mirror descent algorithm in online optimization problems
• Derivative-free optimization methods
• Adaptive sampling quasi-Newton methods for zeroth-order stochastic optimization

This page was built for publication: Stochastic online optimization. Single-point and multi-point non-linear multi-armed bandits. Convex and strongly-convex case

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2397263)