arXiv:2507.00810cs.AImath.OC2025-07
提出一种解决非独立同分布学习问题的鲁棒算法并证明收敛性。
A Robust Algorithm for Non-IID Machine Learning Problems with Convergence Analysis
- 结合非光滑优化与二次规划设计迭代算法。
- 在梯度连续有界条件下证明算法收敛。
- 适用于不平衡学习、鲁棒优化等场景。
本文提出一种基于非光滑优化、二次规划与迭代过程的改进数值算法，用于求解极小极大问题。在梯度连续性和有界性等较弱假设下，给出了该算法的严格收敛性证明。该算法可广泛应用于鲁棒优化、不平衡学习等领域。
原文摘要 · Abstract (English)
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.
优化算法非IID收敛分析
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。