Guardado en:
Detalles Bibliográficos
Autores principales: Li, Tao, Meng, Cheng, Xu, Hongteng, Yu, Jun
Formato: Preprint
Publicado: 2022
Materias:
Acceso en línea:https://arxiv.org/abs/2205.15059
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911771594326016
author Li, Tao
Meng, Cheng
Xu, Hongteng
Yu, Jun
author_facet Li, Tao
Meng, Cheng
Xu, Hongteng
Yu, Jun
contents Distribution comparison plays a central role in many machine learning tasks like data classification and generative modeling. In this study, we propose a novel metric, called Hilbert curve projection (HCP) distance, to measure the distance between two probability distributions with low complexity. In particular, we first project two high-dimensional probability distributions using Hilbert curve to obtain a coupling between them, and then calculate the transport distance between these two distributions in the original space, according to the coupling. We show that HCP distance is a proper metric and is well-defined for probability measures with bounded supports. Furthermore, we demonstrate that the modified empirical HCP distance with the $L_p$ cost in the $d$-dimensional space converges to its population counterpart at a rate of no more than $O(n^{-1/2\max\{d,p\}})$. To suppress the curse-of-dimensionality, we also develop two variants of the HCP distance using (learnable) subspace projections. Experiments on both synthetic and real-world data show that our HCP distance works as an effective surrogate of the Wasserstein distance with low complexity and overcomes the drawbacks of the sliced Wasserstein distance.
format Preprint
id arxiv_https___arxiv_org_abs_2205_15059
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Hilbert Curve Projection Distance for Distribution Comparison
Li, Tao
Meng, Cheng
Xu, Hongteng
Yu, Jun
Machine Learning
Distribution comparison plays a central role in many machine learning tasks like data classification and generative modeling. In this study, we propose a novel metric, called Hilbert curve projection (HCP) distance, to measure the distance between two probability distributions with low complexity. In particular, we first project two high-dimensional probability distributions using Hilbert curve to obtain a coupling between them, and then calculate the transport distance between these two distributions in the original space, according to the coupling. We show that HCP distance is a proper metric and is well-defined for probability measures with bounded supports. Furthermore, we demonstrate that the modified empirical HCP distance with the $L_p$ cost in the $d$-dimensional space converges to its population counterpart at a rate of no more than $O(n^{-1/2\max\{d,p\}})$. To suppress the curse-of-dimensionality, we also develop two variants of the HCP distance using (learnable) subspace projections. Experiments on both synthetic and real-world data show that our HCP distance works as an effective surrogate of the Wasserstein distance with low complexity and overcomes the drawbacks of the sliced Wasserstein distance.
title Hilbert Curve Projection Distance for Distribution Comparison
topic Machine Learning
url https://arxiv.org/abs/2205.15059