PulseAugur
中
实时 07:29:45
English(EN) High-Probability Convergence of Clipped SGD under Heavy-Tailed Noise and $(L_0,L_1)$-Smoothness

arXiv新论文详述高级SGD优化技术 · 已追踪2个来源

作者 PulseAugur 编辑部 · [2 个来源] ·

arXiv上发布的两篇新研究论文探讨了随机梯度下降（SGD）的高级优化技术。第一篇论文“常数步长SGD的尖锐平稳高斯近似”（Sharp Stationary Gaussian Approximation for Constant-Stepsize SGD），作者是Junghoon Seo，在特定条件下为用高斯分布近似SGD的不变定律提供了理论框架。第二篇论文“重尾噪声和$(L_0,L_1)$-平滑下裁剪SGD的高概率收敛性”（High-Probability Convergence of Clipped SGD under Heavy-Tailed Noise and (L0,L1)-Smoothness），作者是Eduard Gorbunov，解决了在处理重尾噪声时裁剪SGD的收敛性挑战，为凸目标函数提供了改进的高概率保证。 AI

影响 这些论文在优化算法方面提供了理论进展，有可能提高训练大型机器学习模型的效率和鲁棒性。

排序理由 arXiv上发表的两篇学术论文，详述了机器学习优化算法的理论进展。

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 →

arXiv新论文详述高级SGD优化技术 · 已追踪2个来源

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
arXiv上发表的两篇学术论文，详述了机器学习优化算法的理论进展。
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
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
8 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [2]

  1. arXiv cs.LG TIER_1 English(EN) · Junghoon Seo ·

    常步长SGD的锐固定高斯近似

    arXiv:2609.39144v2 Announce Type: new Abstract: We prove a sharp Gaussian approximation for the invariant law of constant-stepsize SGD with bounded additive noise generated by an exogenous uniformly ergodic Markov chain. For a smooth, strongly convex objective with a Lipschitz He…

  2. arXiv cs.LG TIER_1 English(EN) · Taha El Bakkali El Kadi, Savelii Chezhegov, Aleksandr Beznosikov, Samuel Horv\'ath, Eduard Gorbunov ·

    重尾噪声和$(L_0,L_1)$-平滑下裁剪SGD的高概率收敛

    arXiv:2505.20817v3 Announce Type: replace-cross Abstract: Gradient clipping is widely used in language-model training to control heavy-tailed gradient noise and can improve convergence guarantees over stochastic gradient descent (SGD) under $(L_0,L_1)$-smoothness. Under these joi…

相关实体

相关话题