Variance-Aware Estimation of Kernel Mean Embedding. (arXiv:2210.06672v1 [math.ST])

An important feature of kernel mean embeddings (KME) is that the rate of
convergence of the empirical KME to the true distribution KME can be bounded
independently of the dimension of the space, properties of the distribution and
smoothness features of the kernel. We show how to speed-up convergence by
leveraging variance information in the RKHS. Furthermore, we show that even
when such information is a priori unknown, we can efficiently estimate it from
the data, recovering the desiderata of …

arxiv embedding kernel math mean variance