为 Moreau--Yosida 未调整 Langevin 采样建立新界限

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-02 04:00

研究人员为 Moreau--Yosida 未调整 Langevin 算法 (MYULA) 建立了近乎线性的精度界限。该分析提供了一个明确的步长条件，在该条件下，相对于 Moreau 平滑目标的不变测度偏差被限制在 $\\widetilde O(h)\$。这项工作结合了 Moreau 近似偏差和 Wasserstein 收缩，确定 $\\widetilde O(\\varepsilon^{-1})\$ 次迭代足以实现 N 次迭代定律所需的精度。利用基于泊松的估计将二阶平稳残差转换为 Wasserstein 界限，直接限制了平稳误差，而无需第三阶导数或 Lipschitz Hessian。 AI

影响为采样算法建立了理论界限，有可能提高机器学习模型训练的效率。

排序理由这是一篇详细介绍采样算法理论进展的研究论文。[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: 13 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 这是一篇详细介绍采样算法理论进展的研究论文。[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) · Yuchen Xin, Zhihua Zhang · 2026-10-02 04:00

Near-Linear Accuracy Bounds for Moreau--Yosida Unadjusted Langevin Sampling

arXiv:2609.40193v1 Announce Type: new Abstract: We establish near-linear accuracy bounds for the classical Moreau--Yosida unadjusted Langevin algorithm (MYULA). The target is $\pi\propto e^{-f-g}$, where $f\in C^2(\mathbb{R}^d)$ is $m$-strongly convex with Lipschitz gradient and …

本文如何被排名

报道来源 [1]

Near-Linear Accuracy Bounds for Moreau--Yosida Unadjusted Langevin Sampling

相关实体

相关话题