A Robust Algorithm for Non-IID Machine Learning Problems with Convergence Analysis

Qing Xu, Xiaohua Xuan
7/1/2025
cs.AImath.OC

No confident code implementation found for this paper. 3 possible matches can be shown below.

Abstract

In this paper, we propose an improved numerical algorithm for solving minimax problems based on nonsmooth optimization, quadratic programming and iterative process. We also provide a rigorous proof of convergence for our algorithm under some mild assumptions, such as gradient continuity and boundedness. Such an algorithm can be widely applied in various fields such as robust optimization, imbalanced learning, etc.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 3 weaker matches are hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Fundamental Benefit of Alternating Updates in Minimax Optimization

84% match1 repo102026

EXOTIC: An Exact, Optimistic, Tree-Based Algorithm for Min-Max Optimization

82% match2025

Robust and Faster Zeroth-Order Minimax Optimization: Complexity and Applications

81% match2026

Enhanced Adaptive Gradient Algorithms for Nonconvex-PL Minimax Optimization

81% match2023

Can Decentralized Stochastic Minimax Optimization Algorithms Converge Linearly for Finite-Sum Nonconvex-Nonconcave Problems?

80% match2023

Escaping limit cycles: Global convergence for constrained nonconvex-nonconcave minimax problems

79% match1 repo52023

Cite this paper

@article{xu2025robust,
  title  = {A Robust Algorithm for Non-IID Machine Learning Problems with Convergence Analysis},
  author = {Qing Xu and Xiaohua Xuan},
  year   = {2025},
  eprint = {2507.00810},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2507.00810v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2507.00810.svg)](https://codeofpaper.com/paper/2507.00810)

Discussion