PulseAugur
实时 10:16:31

新方法为Bregman ADMM提供二阶KKT保证

研究人员开发了一种新颖的方法来分析非凸和非Lipschitz优化问题的Bregman ADMM。该方法用双边相对平滑条件取代了标准的Lipschitz梯度假设,该条件涉及相对于Bregman核的Hessian比较。分析表明,在此条件下,迭代以高概率收敛到严格鞍点,从而导致极限KKT点的几乎确定性二阶平稳性。该工作通过多块星形共识公式扩展到分布式优化,并包括矩阵和张量分解的数值实验。 AI

影响 推动了机器学习模型的优化理论,可能提高复杂非凸问题的训练效率和收敛性。

排序理由 该集群包含一篇详细介绍优化算法理论进展的研究论文。

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

新方法为Bregman ADMM提供二阶KKT保证

报道来源 [2]

  1. arXiv cs.LG TIER_1 English(EN) · Shuang Li, Zhihui Zhu, Qiuwei Li ·

    Second-Order KKT Guarantees for Bregman ADMM in Nonconvex and Non-Lipschitz Optimization

    arXiv:2606.28307v1 Announce Type: cross Abstract: We analyze Bregman ADMM for nonconvex linearly constrained problems under two-sided relative smoothness, a condition that replaces the standard Lipschitz gradient assumption with a Hessian comparison relative to a Bregman kernel. …

  2. arXiv cs.LG TIER_1 English(EN) · Qiuwei Li ·

    Second-Order KKT Guarantees for Bregman ADMM in Nonconvex and Non-Lipschitz Optimization

    We analyze Bregman ADMM for nonconvex linearly constrained problems under two-sided relative smoothness, a condition that replaces the standard Lipschitz gradient assumption with a Hessian comparison relative to a Bregman kernel. This setting covers polynomial objectives arising …