Variance-Aware Estimation of Kernel Mean Embedding

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wolfer, Geoffrey, Alquier, Pierre
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909580552830976
author Wolfer, Geoffrey
Alquier, Pierre
author_facet Wolfer, Geoffrey
Alquier, Pierre
contents 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 reproducing kernel Hilbert space. Furthermore, we show that even when such information is a priori unknown, we can efficiently estimate it from the data, recovering the desiderata of a distribution agnostic bound that enjoys acceleration in fortuitous settings. We further extend our results from independent data to stationary mixing sequences and illustrate our methods in the context of hypothesis testing and robust parametric estimation.
format Preprint
id arxiv_https___arxiv_org_abs_2210_06672
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Variance-Aware Estimation of Kernel Mean Embedding
Wolfer, Geoffrey
Alquier, Pierre
Statistics Theory
Machine Learning
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 reproducing kernel Hilbert space. Furthermore, we show that even when such information is a priori unknown, we can efficiently estimate it from the data, recovering the desiderata of a distribution agnostic bound that enjoys acceleration in fortuitous settings. We further extend our results from independent data to stationary mixing sequences and illustrate our methods in the context of hypothesis testing and robust parametric estimation.
title Variance-Aware Estimation of Kernel Mean Embedding
topic Statistics Theory
Machine Learning
url https://arxiv.org/abs/2210.06672