新的SGD方法在大规模训练中实现了尖锐的收敛率

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-07 04:00

研究人员开发了一种名为“居中排列前缀随机重排随机梯度下降（SGD）”的新方法。该技术旨在通过优化数据处理方式来提高大型数据集训练的效率。所提出的方法实现了尖锐的收敛率，特别是对于具有Lipschitz连续Hessian的强凸函数，并且即使在目标函数的某些部分是非凸的情况下也能提供改进。 AI

影响这项研究通过改进优化算法，可能导致更有效地训练大型机器学习模型。

排序理由该集群包含一篇详细介绍机器学习新优化方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

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

本文如何被排名

Signal score: 33 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍机器学习新优化方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
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。

arXiv cs.LG TIER_1 English(EN) · Jiaxiang Li · 2026-09-07 04:00

SGD with Random Reshuffling的中心置换前缀：锐速率、H"older几何和复合近邻扩展

arXiv:2609.04578v1 Announce Type: cross Abstract: We study stochastic gradient descent with random reshuffling for finite sums \[ F(x)=\frac1n\sum_{i=1}^n f_i(x). \] For fresh reshuffling with a constant component stepsize, if each $f_i$ has an $L$-Lipschitz gradient and the aver…