Back to Search Start Over

Intrinsic Dimension Estimation Using Wasserstein Distances

Authors :
Block, Adam
Jia, Zeyu
Polyanskiy, Yury
Rakhlin, Alexander
Publication Year :
2021

Abstract

It has long been thought that high-dimensional data encountered in many practical machine learning tasks have low-dimensional structure, i.e., the manifold hypothesis holds. A natural question, thus, is to estimate the intrinsic dimension of a given population distribution from a finite sample. We introduce a new estimator of the intrinsic dimension and provide finite sample, non-asymptotic guarantees. We then apply our techniques to get new sample complexity bounds for Generative Adversarial Networks (GANs) depending only on the intrinsic dimension of the data.

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2106.04018
Document Type :
Working Paper