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 1206.4664cs.LGstat.ML
收藏

f-发散的紧变分表示及其概率测度限制

Tighter Variational Representations of f-Divergences via Restriction to Probability Measures

Research School of Computer Science, Australian National University(澳大利亚国立大学计算机科学研究学院);NICTA

Avraham Ruderman, Mark Reid, Dario Garcia-Garcia, James Petterson

摘要:

我们表明,目前在文献中使用的f-发散的变分表示可以收紧。这对最近基于这种表示提出的一些方法有影响。作为示例应用,我们使用更严格的表示来推导基于两个独立同分布的通用f-发散估计量样本,并推导出该估计器的对偶程序,该估计器在经验上表现良好。我们还指出了我们的估计和MMD之间的连接。

英文摘要:

We show that the variational representations for f-divergences currently used in the literature can be tightened. This has implications to a number of methods recently proposed based on this representation. As an example application we use our tighter representation to derive a general f-divergence estimator based on two i.i.d. samples and derive the dual program for this estimator that performs well empirically. We also point out a connection between our estimator and MMD.

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。

↑