English(EN) Optimal Learning Rate Schedules under Functional Scaling Laws: Power Decay and Warmup-Stable-Decay

函数缩放定律下探索最优学习率调度

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-15 04:00

本文探讨了机器学习模型最优学习率调度，特别是在函数缩放定律（FSL）框架下。文章确定了一个基于任务难度和模型容量的关键过渡点，该点决定了早期幂衰减还是预热-稳定-衰减调度更有效。研究还表明，精确的衰减形状调整可能不如之前认为的那么关键，分数调度可以达到最优收敛率。 AI

影响为优化模型训练提供了理论见解，可能导致更高效的学习过程。

排序理由详细介绍机器学习优化理论发现的学术论文。 [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: 13 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍机器学习优化理论发现的学术论文。 [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) · Binghui Li, Zilin Wang, Fengling Chen, Shiyang Zhao, Ruiheng Zheng, Lei Wu · 2026-09-15 04:00

函数缩放定律下的最优学习率调度：幂衰减与预热-稳定-衰减

arXiv:2602.06797v3 Announce Type: replace-cross Abstract: We study optimal learning rate (LR) schedules under the functional scaling law (FSL) framework (Li et al., 2025), which decomposes training dynamics into signal learning and noise forgetting. In power-law kernel regression…