English(EN) Improved Guarantees for Langevin Monte Carlo with Average Smoothness

Langevin Monte Carlo 方法获得改进的理论保证

作者 PulseAugur 编辑部 · [3 个来源] · 2026-05-29 15:15

研究人员为机器学习中的 Langevin Monte Carlo 方法开发了新的理论界限。该工作侧重于改进强对数凹陷设置下的非渐近保证，并使用 Wasserstein 距离来衡量误差。一项关键发现是，离散化误差取决于平均坐标平滑度而不是全局平滑度，这为广义线性模型等特定应用提供了潜在的改进。 AI

影响改进了对机器学习中使用的采样方法的理论理解，可能导致更有效的模型训练。

排序理由该集群包含一篇详细介绍机器学习算法理论改进的学术论文。

AI 生成摘要 · Google Gemini · 来自 3 个来源。我们如何撰写摘要 →

报道来源 [3]

arXiv cs.LG TIER_1 English(EN) · Arnak S. Dalalyan, Avetik Karagulyan · 2026-06-01 04:00

具有平均光滑度的 Langevin Monte Carlo 的改进保证

arXiv:2605.31413v1 Announce Type: cross Abstract: We establish improved nonasymptotic bounds for Langevin Monte Carlo in the strongly log-concave setting, when the error is measured by the Wasserstein distance. The main result shows that the discretization error is governed by an…
arXiv cs.LG TIER_1 English(EN) · Avetik Karagulyan · 2026-05-29 15:15

具有平均光滑度的 Langevin Monte Carlo 的改进保证

We establish improved nonasymptotic bounds for Langevin Monte Carlo in the strongly log-concave setting, when the error is measured by the Wasserstein distance. The main result shows that the discretization error is governed by an average coordinate-wise smoothness constant, rath…
arXiv stat.ML TIER_1 English(EN) · Andreas Maurer, Erfan Mirzaei, Massimiliano Pontil · 2026-06-02 04:00

Gibbs和Langevin蒙特卡洛算法在插值区域的泛化

arXiv:2510.06028v3 Announce Type: replace-cross Abstract: This paper provides data-dependent bounds on the expected error of the Gibbs algorithm in the overparameterized interpolation regime, where low training errors are also obtained for impossible data, such as random labels i…