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 2201.13127cs.LGcs.AIstat.ML
收藏

基于最大似然密度比估计的概率发散统一观点:KL发散与积分概率发散的桥接

Unified Perspective on Probability Divergence via Maximum Likelihood Density Ratio Estimation: Bridging KL-Divergence and Integral Probability Metrics

The University of Tokyo(东京大学);CyberAgent, Inc.(赛博艾金特公司);RIKEN Center for Advanced Intelligence Project(理化学研究所先进智能项目中心);Preferred Networks, Inc.(优选网络公司)

Masahiro Kato, Masaaki Imaizumi, Kentaro Minami

摘要:

本文从最大似然密度比估计的角度,给出了Kullback-Leibler(KL)-散度和积分概率度量(IPM)的统一观点。KL-发散和IPM都被广泛应用于生成建模等各个领域。然而,对这些概念的统一理解尚未得到探索。在本文中,我们表明,KL-分歧和IPM可以表示为最大似然不同,只有抽样方案,并使用这个结果,以获得一个统一的形式的IPM和宽松的估计方法。为了发展的估计问题,我们构造了一个无约束的最大似然估计进行DRE与分层抽样方案。我们进一步提出了一类新的概率发散,称为密度比(DRMs),插值KL发散和IPM。除了这些发现,我们还介绍了DRM的一些应用,如DRE和生成对抗网络。在实验中,我们验证了我们提出的方法的有效性。

英文摘要:

This paper provides a unified perspective for the Kullback-Leibler (KL)-divergence and the integral probability metrics (IPMs) from the perspective of maximum likelihood density-ratio estimation (DRE). Both the KL-divergence and the IPMs are widely used in various fields in applications such as generative modeling. However, a unified understanding of these concepts has still been unexplored. In this paper, we show that the KL-divergence and the IPMs can be represented as maximal likelihoods differing only by sampling schemes, and use this result to derive a unified form of the IPMs and a relaxed estimation method. To develop the estimation problem, we construct an unconstrained maximum likelihood estimator to perform DRE with a stratified sampling scheme. We further propose a novel class of probability divergences, called the Density Ratio Metrics (DRMs), that interpolates the KL-divergence and the IPMs. In addition to these findings, we also introduce some applications of the DRMs, such as DRE and generative adversarial networks. In experiments, we validate the effectiveness of our proposed 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。

↑