Hilbert space embeddings and metrics on probability measures

Details Hilbert space embeddings and metrics on probability measures Hilbert space embeddings and metrics on probability measures

2009-07-30

arxiv.org/abs/0907.5309v3

Statistics

Machine Learning

48 pages

Scientific paper

A Hilbert space embedding for probability measures has recently been proposed, with applications including dimensionality reduction, homogeneity testing, and independence testing. This embedding represents any probability measure as a mean element in a reproducing kernel Hilbert space (RKHS). A pseudometric on the space of probability measures can be defined as the distance between distribution embeddings: we denote this as $\gamma_k$, indexed by the kernel function $k$ that defines the inner product in the RKHS. We present three theoretical properties of $\gamma_k$. First, we consider the question of determining the conditions on the kernel $k$ for which $\gamma_k$ is a metric: such $k$ are denoted {\em characteristic kernels}. Unlike pseudometrics, a metric is zero only when two distributions coincide, thus ensuring the RKHS embedding maps all distributions uniquely (i.e., the embedding is injective). While previously published conditions may apply only in restricted circumstances (e.g. on compact domains), and are difficult to check, our conditions are straightforward and intuitive: bounded continuous strictly positive definite kernels are characteristic. Alternatively, if a bounded continuous kernel is translation-invariant on $\bb{R}^d$, then it is characteristic if and only if the support of its Fourier transform is the entire $\bb{R}^d$. Second, we show that there exist distinct distributions that are arbitrarily close in $\gamma_k$. Third, to understand the nature of the topology induced by $\gamma_k$, we relate $\gamma_k$ to other popular metrics on probability measures, and present conditions on the kernel $k$ under which $\gamma_k$ metrizes the weak topology.

Affiliated with

Also associated with

No associations

Rating

Hilbert space embeddings and metrics on probability measures does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Hilbert space embeddings and metrics on probability measures, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Hilbert space embeddings and metrics on probability measures will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-468876