arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2605.26850cs.LG
收藏

从随机插值中学习基于能量的模型:利用时空差异

Learning Energy-Based Models from Stochastic Interpolants using Spatiotemporal Differences

University of Helsinki(赫尔辛基大学);University of Cambridge(剑桥大学);Carnegie Mellon University(卡内基梅隆大学);University of Edinburgh(爱丁堡大学)

Hanlin Yu, RuiKang OuYang, Partha Kaushik, Arto Klami, Michael U. Gutmann, Omar Chehab

AI总结:

提出时空噪声对比估计(stNCE)框架,通过联合时空差异从随机插值中学习能量函数,统一现有方法并实现与最先进密度估计方法竞争的性能。

摘要:

从数据样本中学习基于能量的模型是机器学习中的一个核心问题。许多近期流行的方法,如用于训练基于能量的扩散模型的去噪分数匹配,使用随机插值器通过时间变量索引的不同噪声水平来破坏数据样本。这定义了数据空间和时间上的联合密度,大多数方法通过空间或时间差异来学习其能量。我们识别了这两种方法各自的失败模式。为了解决这些问题,我们提出了时空噪声对比估计(stNCE),一个通过联合时空差异来学习能量的框架。stNCE统一了许多现有方法,并产生了新的训练目标。在图像和分子上的实验表明,其性能与最先进的密度估计方法相竞争。

英文摘要:

Learning an energy-based model from data samples is a central problem in machine learning. Many recent and popular methods, such as denoising score matching for training energy-based diffusion models, use stochastic interpolants to corrupt data samples at different noise levels indexed by a time variable. This defines a joint density over both the data space and time, and most methods learn its energy through either spatial or temporal differences. We identify distinct failure modes for both of these approaches. To solve them, we propose Spatiotemporal Noise-Contrastive Estimation (stNCE), a framework for learning the energy through joint spatiotemporal differences. stNCE unifies many existing methods and leads to new training objectives. Experiments on images and molecules demonstrate performance competitive with state-of-the-art density estimation methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑