新框架从有偏样本中重建随机动力学

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

研究人员引入了Langevin-Informed Transfer Learning (LITL)，一个新颖的框架，旨在仅使用黑盒反馈从有偏或静态样本中重建目标Langevin动力学。LITL专注于学习目标无穷小生成器和投影漂移的光谱结构，从而实现动力学重建和慢流形梯度场估计。该框架得到了关键估计的有限样本保证的支持，并在恢复物理过渡时间尺度、从生成模型构建动力学结构以及实现神经网络的事后潜在控制方面取得了实证成功。 AI

影响能够从有限数据中重建随机动力学，可能推动生成模型和科学模拟的发展。

排序理由介绍新机器学习框架的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv stat.ML 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: 1 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 介绍新机器学习框架的学术论文。[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, model release, 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: 1 days old; Coverage has settled into its steady-state source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv stat.ML TIER_1 English(EN) · Vladimir R. Kostic, Karim Lounici, H\'el\`ene Halconruy, Timoth\'ee Devergne, Michele Parrinello, Massimiliano Pontil · 2026-10-02 04:00

Langevin-Informed Transfer Learning: Replacing Target Samples by Black-Box Feedback

arXiv:2610.01522v1 Announce Type: cross Abstract: Many scientific and machine learning systems, from molecular dynamics to diffusion models and beyond, are governed by stochastic dynamics with low-dimensional structure, evolving on slow timescales. However, target trajectories, u…

本文如何被排名

报道来源 [1]

Langevin-Informed Transfer Learning: Replacing Target Samples by Black-Box Feedback

相关实体

相关话题