Characteristic and Universal Tensor Product Kernels - Archive ouverte HAL Access content directly
Journal Articles Journal of Machine Learning Research Year : 2018

Characteristic and Universal Tensor Product Kernels


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.
Fichier principal
Vignette du fichier
17-492.pdf (445.46 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-01585727 , version 1 (11-09-2017)
hal-01585727 , version 2 (13-05-2018)
hal-01585727 , version 3 (02-08-2018)




Zoltán Szabó, Bharath K Sriperumbudur. Characteristic and Universal Tensor Product Kernels. Journal of Machine Learning Research, 2018, 18, pp.233. ⟨hal-01585727v3⟩
396 View
588 Download



Gmail Mastodon Facebook X LinkedIn More