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 2311.02868cs.LG
收藏

在不变性下估计概率分歧的样本复杂度界限

Sample Complexity Bounds for Estimating Probability Divergences under Invariances

MIT CSAIL(麻省理工学院计算机科学与人工智能实验室);TU Munich(慕尼黑工业大学)

Behrooz Tahmasebi, Stefanie Jegelka

AI总结:

本文研究了在不变性下估计概率分歧的样本复杂度,发现群不变性可减少样本复杂度并提高收敛率。

摘要:

在许多数据生成模型中,群不变概率分布出现在图、点云和图像中。在实践中,往往需要估计此类分布之间的分歧。在本工作中,我们研究了任何光滑动作的李群在流形上的不变性如何在估计1-瓦瑟斯坦距离、索波列夫积分概率度量(索波列夫IPMs)、最大均值差异(MMD)以及密度估计问题(在L²和L∞距离下)时提高样本复杂度。我们的结果表明有两种收益:(1)通过乘以群大小(对于有限群)或归一化商空间的体积(对于正维度的群)来减少样本复杂度;(2)对于正维度的群,改进收敛率的指数。这些结果对于正维度的群是全新的,并扩展了最近针对有限群动作的界限。

英文摘要:

Group-invariant probability distributions appear in many data-generative models in machine learning, such as graphs, point clouds, and images. In practice, one often needs to estimate divergences between such distributions. In this work, we study how the inherent invariances, with respect to any smooth action of a Lie group on a manifold, improve sample complexity when estimating the 1-Wasserstein distance, the Sobolev Integral Probability Metrics (Sobolev IPMs), the Maximum Mean Discrepancy (MMD), and also the complexity of the density estimation problem (in the $L^2$ and $L^\infty$ distance). Our results indicate a two-fold gain: (1) reducing the sample complexity by a multiplicative factor corresponding to the group size (for finite groups) or the normalized volume of the quotient space (for groups of positive dimension); (2) improving the exponent in the convergence rate (for groups of positive dimension). These results are completely new for groups of positive dimension and extend recent bounds for finite group actions.

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。

↑