Characteristic and universal tensor product kernels

Zoltán Szabó, Bharath K. Sriperumbudur

Research output: Contribution to journalArticlepeer-review

22 Scopus citations

Abstract

Maximum mean discrepancy (MMD), also called energy distance or N-distance in statistics and Hilbert-Schmidt independence criterion (HSIC), specifically distance covariance in statistics, are among the most popular and successful approaches to quantify the difference and independence of random variables, respectively. Thanks to their kernel-based foundations, MMD and HSIC are applicable on a wide variety of domains. Despite their tremendous success, quite little is known about when HSIC characterizes independence and when MMD with tensor product kernel can discriminate probability distributions. In this paper, we answer these questions by studying various notions of characteristic property of the tensor product kernel.

Original languageEnglish (US)
Pages (from-to)1-29
Number of pages29
JournalJournal of Machine Learning Research
Volume18
StatePublished - 2018

All Science Journal Classification (ASJC) codes

  • Software
  • Artificial Intelligence
  • Control and Systems Engineering
  • Statistics and Probability

Fingerprint

Dive into the research topics of 'Characteristic and universal tensor product kernels'. Together they form a unique fingerprint.

Cite this