Distributed optimization for degenerate loss functions arising from over-parameterization

DOI10.1016/J.ARTINT.2021.103575MaRDI QIDQ2060697zbMATH OpenOpenAlexFDO

Authors Chi Zhang, Qianxiao Li

Publication date 13 December 2021

Published in Artificial Intelligence (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.artint.2021.103575

zbMATH Keywords

deep learningdistributed optimizationover-parameterization

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Agent technology and artificial intelligence (68T42) Distributed algorithms (68W15) Convex programming (90C25) Nonlinear programming (90C30)

Recommendations

• Optimal convergence rates for convex distributed optimization in networks
• Convergence of distributed gradient-tracking-based optimization algorithms with random graphs
• An accelerated communication-efficient primal-dual optimization framework for structured machine learning
• scientific article; zbMATH DE number 6982986
• Optimal Methods for Convex Risk-Averse Distributed Optimization

Cites work

• Block-iterative projection methods for parallel computation of solutions to convex feasibility problems
• Convergence rate analysis and error bounds for projection algorithms in convex feasibility problems
• Distributed optimization with arbitrary local solvers
• Dual Averaging for Distributed Optimization: Convergence Analysis and Network Scaling
• Error bounds and convergence analysis of feasible descent methods: A general approach
• scientific article; zbMATH DE number 51132 (Why is no real title available?)
• scientific article; zbMATH DE number 6982986 (Why is no real title available?)
• scientific article; zbMATH DE number 3313108 (Why is no real title available?)
• On Projection Algorithms for Solving Convex Feasibility Problems
• Randomized projection methods for convex feasibility: conditioning and convergence rates
• The implicit convex feasibility problem and its application to adaptive image denoising

Cited in

(1)

• Decentralized stochastic sharpness-aware minimization algorithm

This page was built for publication: Distributed optimization for degenerate loss functions arising from over-parameterization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2060697)