PulseAugur
中
实时 07:10:54

为非扩张随机逼近迭代确立了新的理论界限

本文为非扩张随机逼近(SA)迭代确立了新的理论界限,特别关注Krasnoselskii-Mann(KM)方法。研究分析了关于欧几里得范数非扩张的固定点映射,并利用多项式衰减的步长。研究结果详细阐述了在三种不同噪声条件下的最优界限,表明虽然某些条件与无噪声迭代相匹配,但其他条件则需要可平方和的步长才能收敛。该框架应用于随机梯度下降和共激励博弈中的学习等算法。 AI

影响 为机器学习中使用的优化算法提供了理论基础,可能提高训练效率。

排序理由 发表在arXiv上的学术论文,详细介绍了随机逼近方面的理论进展。[lever_c_demoted from research: ic=1 ai=0.7]

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

为非扩张随机逼近迭代确立了新的理论界限

本文如何被排名

Signal score
24 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
发表在arXiv上的学术论文,详细介绍了随机逼近方面的理论进展。[lever_c_demoted from research: ic=1 ai=0.7]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, other
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

  1. arXiv cs.LG TIER_1 English(EN) · Ramanan Tamizholi, Siddharth Chandak, Rahul Singh ·

    非扩张随机逼近的最优末次迭代界限

    arXiv:2611.13846v1 Announce Type: cross Abstract: We establish last-iterate mean-square residual bounds for nonexpansive stochastic approximation (SA), or stochastic Krasnoselskii-Mann (KM) iterations. In particular, we consider fixed-point mappings that are nonexpansive with res…