English(EN) Accelerating Non-Smooth and Heavy-Tailed Sampling

新的非可逆 Langevin 动力学加速了复杂分布的采样

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-09 04:00

研究人员引入了非可逆锚定 Langevin 动力学 (NALD) 和非可逆反射锚定 Langevin 动力学 (NRALD)，以改进机器学习中的采样。这些新方法旨在处理非光滑和重尾目标分布，即使在约束空间中，也无需计算目标密度的导数。通过引入循环漂移和流势，NALD 和 NRALD 可以比其可逆对应物实现更快的收敛，这已通过理论分析和数值实验得到证明。 AI

影响这些新的采样方法可以提高处理非光滑或重尾数据分布的复杂机器学习模型的训练效率。

排序理由该集群包含一篇详细介绍机器学习中新采样算法的学术论文。[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: 0 / 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中新采样算法的学术论文。[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: 16 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 [1]

arXiv cs.LG TIER_1 English(EN) · Pervez Ali, Xiaoyu Wang, Yingli Wang, Lingjiong Zhu · 2026-10-09 04:00

加速非光滑和重尾采样

arXiv:2610.11139v1 Announce Type: cross Abstract: Anchored Langevin dynamics (ALD) is useful for non-smooth sampling where the density of the target distribution is possibly non-differentiable and heavy-tailed; reflected anchored Langevin dynamics (RALD) can sample possibly non-d…

本文如何被排名

报道来源 [1]

加速非光滑和重尾采样

相关实体

相关话题