English(EN) High-Probability Convergence of SGD via Batched Updates

新的批量SGD方法提供高概率收敛保证

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-14 04:00

研究人员推出了一种新颖的随机梯度下降（SGD）变体——批量SGD，旨在为优化问题实现高概率收敛保证。该方法将在线样本划分为多个周期（epochs），每个周期使用一个精炼的梯度估计进行一次更新。该方法通过避免严格的假设和辅助序列来简化分析，为强凸和非凸目标都提供了近乎最优的收敛速率。此外，批量SGD还扩展到联邦学习领域，为该领域提供了首个具有对数通信复杂度和对数据异质性韧性的高概率保证。 AI

影响引入了一种更鲁棒的优化技术，可以改进大型AI模型的训练。

排序理由详细介绍新优化方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

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 →

本文如何被排名

Signal score: 27 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍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。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Feng Zhu, Robert W. Heath Jr., Aritra Mitra · 2026-09-14 04:00

SGD通过批量更新实现高概率收敛

arXiv:2609.12765v1 Announce Type: cross Abstract: Stochastic gradient descent (SGD) is the primary workhorse for large-scale optimization. While the average behavior of its iterates, typically characterized by mean-squared error bounds, is well-understood, obtaining high-probabil…

本文如何被排名

报道来源 [1]

SGD通过批量更新实现高概率收敛

相关实体

相关话题