UCL logo

UCL Discovery

UCL home » Library Services » Electronic resources » UCL Discovery

Characteristic kernels on groups and semigroups

Fukumizu, K; Sriperumbudur, B; Gretton, A; Schölkopf, B; (2009) Characteristic kernels on groups and semigroups. In: (pp. pp. 473-480).

Full text not available from this repository.

Abstract

Embeddings of random variables in reproducing kernel Hilbert spaces (RKHSs) may be used to conduct statistical inference based on higher order moments. For sufficiently rich (characteristic) RKHSs, each probability distribution has a unique embedding, allowing all statistical properties of the distribution to be taken into consideration. Necessary and sufficient conditions for an RKHS to be characteristic exist for ℝ n . In the present work, conditions are established for an RKHS to be characteristic on groups and semigroups. Illustrative examples are provided, including characteristic kernels on periodic domains, rotation matrices, and ℝ + n .

Type: Proceedings paper
Title: Characteristic kernels on groups and semigroups
ISBN-13: 9781605609492
URI: http://discovery.ucl.ac.uk/id/eprint/1334312
Downloads since deposit
0Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item