Controlling stochastic gradient descent using stochastic approximation for robust distributed optimization

DOI10.3934/NACO.2024041MaRDI QIDQ7026650zbMATH OpenFDO

Authors Adit Jain, Vikram Krishnamurthy

Publication date 17 February 2025

Published in Numerical Algebra, Control and Optimization (Search for Journal in Brave)

Full work available at URL https://doi.org/10.3934/NACO.2024041

zbMATH Keywords

distributed optimizationMarkov decision processesstochastic approximation

Mathematics Subject Classification ID

Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.) (60J20) Stochastic approximation (62L20) Markov and semi-Markov decision processes (90C40) Rationality and learning in game theory (91A26) Decision theory (91B06)

Cites work

• A Dynamical Games Approach to Transmission-Rate Adaptation in Multimedia WLAN
• A finite algorithm for the switching control stochastic game
• Advanced Lectures on Machine Learning
• Discrete-event control of stochastic networks: multimodularity and regularity.
• scientific article; zbMATH DE number 1972910 (Why is no real title available?)
• Learner-Private Convex Optimization
• Models for network dynamics: A Markovian framework*
• Monotonicity of Constrained Optimal Transmission Policies in Correlated Fading Channels With ARQ
• Optimal policies for controlled Markov chains with a constraint
• Private sequential learning
• Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming

This page was built for publication: Controlling stochastic gradient descent using stochastic approximation for robust distributed optimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7026650)