Panda: partially approximate Newton methods for distributed minimax optimization with unbalanced dimensions

DOI10.1007/S10994-025-06813-1MaRDI QIDQ6903669zbMATH OpenFDO

Authors Minheng Xiao, Chengchang Liu, Cheng Chen, John C. S. Lui, Sen Na

Publication date 10 November 2025

Published in Machine Learning (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.1007/S10994-025-06813-1

zbMATH Keywords

distributed optimizationfairness-aware machine learningfew-shot learningminimax optimization

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Applications of mathematical programming (90C90)

Cites work

• 10.1162/153244303321897726
• A Modified Forward-Backward Splitting Method for Maximal Monotone Mappings
• Approximate Newton methods
• Cubic regularized Newton method for the saddle point models: a global and local convergence analysis
• Distributionally Robust Stochastic Optimization with Wasserstein Distance
• Extensions of Lipschitz mappings into a Hilbert space
• Finite-Dimensional Variational Inequalities and Complementarity Problems
• Greedy quasi-Newton methods with explicit superlinear convergence
• Hessian averaging in stochastic Newton methods achieves superlinear convergence
• scientific article; zbMATH DE number 3534286 (Why is no real title available?)
• scientific article; zbMATH DE number 1243371 (Why is no real title available?)
• Low-distortion subspace embeddings in input-sparsity time and applications to robust linear regression
• Low-rank approximation and regression in input sparsity time
• Nesterov's acceleration for approximate Newton
• Projected reflected gradient methods for monotone variational inequalities
• Robust optimization-methodology and applications
• Sketched ridge regression: optimization perspective, statistical perspective, and model averaging
• Sub-sampled Newton methods
• Subgradient methods for saddle-point problems

This page was built for publication: Panda: partially approximate Newton methods for distributed minimax optimization with unbalanced dimensions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6903669)