A contribution to Optimal Transport on incomparable spaces

11/09/2020
by   Titouan Vayer, et al.
0

Optimal Transport is a theory that allows to define geometrical notions of distance between probability distributions and to find correspondences, relationships, between sets of points. Many machine learning applications are derived from this theory, at the frontier between mathematics and optimization. This thesis proposes to study the complex scenario in which the different data belong to incomparable spaces. In particular we address the following questions: how to define and apply Optimal Transport between graphs, between structured data? How can it be adapted when the data are varied and not embedded in the same metric space? This thesis proposes a set of Optimal Transport tools for these different cases. An important part is notably devoted to the study of the Gromov-Wasserstein distance whose properties allow to define interesting transport problems on incomparable spaces. More broadly, we analyze the mathematical properties of the various proposed tools, we establish algorithmic solutions to compute them and we study their applicability in numerous machine learning scenarii which cover, in particular, classification, simplification, partitioning of structured data, as well as heterogeneous domain adaptation.

READ FULL TEXT

page 1

page 12

research
02/10/2020

CO-Optimal Transport

Optimal transport (OT) is a powerful geometric and probabilistic tool fo...
research
04/05/2021

Quantized Gromov-Wasserstein

The Gromov-Wasserstein (GW) framework adapts ideas from optimal transpor...
research
03/01/2018

Computational Optimal Transport

Optimal Transport (OT) is a mathematical gem at the interface between pr...
research
11/22/2021

Cycle Consistent Probability Divergences Across Different Spaces

Discrepancy measures between probability distributions are at the core o...
research
10/09/2019

Learning with minibatch Wasserstein : asymptotic and gradient properties

Optimal transport distances are powerful tools to compare probability di...
research
02/12/2022

Depth profiles and the geometric exploration of random objects through optimal transport

We propose new tools for the geometric exploration of data objects takin...
research
06/12/2023

Generating Synthetic Datasets by Interpolating along Generalized Geodesics

Data for pretraining machine learning models often consists of collectio...

Please sign up or login with your details

Forgot password? Click here to reset