Energy-Guided Continuous Entropic Barycenter Estimation for General Costs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kolesov, Alexander, Mokrov, Petr, Udovichenko, Igor, Gazdieva, Milena, Pammer, Gudmund, Kratsios, Anastasis, Burnaev, Evgeny, Korotin, Alexander
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913674553196544
author Kolesov, Alexander
Mokrov, Petr
Udovichenko, Igor
Gazdieva, Milena
Pammer, Gudmund
Kratsios, Anastasis
Burnaev, Evgeny
Korotin, Alexander
author_facet Kolesov, Alexander
Mokrov, Petr
Udovichenko, Igor
Gazdieva, Milena
Pammer, Gudmund
Kratsios, Anastasis
Burnaev, Evgeny
Korotin, Alexander
contents Optimal transport (OT) barycenters are a mathematically grounded way of averaging probability distributions while capturing their geometric properties. In short, the barycenter task is to take the average of a collection of probability distributions w.r.t. given OT discrepancies. We propose a novel algorithm for approximating the continuous Entropic OT (EOT) barycenter for arbitrary OT cost functions. Our approach is built upon the dual reformulation of the EOT problem based on weak OT, which has recently gained the attention of the ML community. Beyond its novelty, our method enjoys several advantageous properties: (i) we establish quality bounds for the recovered solution; (ii) this approach seamlessly interconnects with the Energy-Based Models (EBMs) learning procedure enabling the use of well-tuned algorithms for the problem of interest; (iii) it provides an intuitive optimization scheme avoiding min-max, reinforce and other intricate technical tricks. For validation, we consider several low-dimensional scenarios and image-space setups, including non-Euclidean cost functions. Furthermore, we investigate the practical task of learning the barycenter on an image manifold generated by a pretrained generative model, opening up new directions for real-world applications. Our code is available at https://github.com/justkolesov/EnergyGuidedBarycenters.
format Preprint
id arxiv_https___arxiv_org_abs_2310_01105
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Energy-Guided Continuous Entropic Barycenter Estimation for General Costs
Kolesov, Alexander
Mokrov, Petr
Udovichenko, Igor
Gazdieva, Milena
Pammer, Gudmund
Kratsios, Anastasis
Burnaev, Evgeny
Korotin, Alexander
Machine Learning
Optimal transport (OT) barycenters are a mathematically grounded way of averaging probability distributions while capturing their geometric properties. In short, the barycenter task is to take the average of a collection of probability distributions w.r.t. given OT discrepancies. We propose a novel algorithm for approximating the continuous Entropic OT (EOT) barycenter for arbitrary OT cost functions. Our approach is built upon the dual reformulation of the EOT problem based on weak OT, which has recently gained the attention of the ML community. Beyond its novelty, our method enjoys several advantageous properties: (i) we establish quality bounds for the recovered solution; (ii) this approach seamlessly interconnects with the Energy-Based Models (EBMs) learning procedure enabling the use of well-tuned algorithms for the problem of interest; (iii) it provides an intuitive optimization scheme avoiding min-max, reinforce and other intricate technical tricks. For validation, we consider several low-dimensional scenarios and image-space setups, including non-Euclidean cost functions. Furthermore, we investigate the practical task of learning the barycenter on an image manifold generated by a pretrained generative model, opening up new directions for real-world applications. Our code is available at https://github.com/justkolesov/EnergyGuidedBarycenters.
title Energy-Guided Continuous Entropic Barycenter Estimation for General Costs
topic Machine Learning
url https://arxiv.org/abs/2310.01105