all AI news
Stochastic optimal transport in Banach Spaces for regularized estimation of multivariate quantiles
Feb. 20, 2024, 5:46 a.m. | Bernard Bercu, J\'er\'emie Bigot, Gauthier Thurin
stat.ML updates on arXiv.org arxiv.org
Abstract: We introduce a new stochastic algorithm for solving entropic optimal transport (EOT) between two absolutely continuous probability measures $\mu$ and $\nu$. Our work is motivated by the specific setting of Monge-Kantorovich quantiles where the source measure $\mu$ is either the uniform distribution on the unit hypercube or the spherical uniform distribution. Using the knowledge of the source measure, we propose to parametrize a Kantorovich dual potential by its Fourier coefficients. In this way, each iteration …
abstract algorithm arxiv continuous distribution math.pr multivariate probability spaces stat.ml stochastic transport type uniform work
More from arxiv.org / stat.ML updates on arXiv.org
Inexact subgradient methods for semialgebraic functions
1 day, 17 hours ago |
arxiv.org
Online and Offline Robust Multivariate Linear Regression
1 day, 17 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Senior Data Scientist
@ ITE Management | New York City, United States