Pith. sign in

A contribution to Optimal Transport on incomparable spaces

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

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.

fields

math.PR 1

years

2025 1

verdicts

ACCEPT 1

representative citing papers

Quadratic-form Optimal Transport

math.PR · 2025-01-08 · accept · novelty 8.0

Quadratic-form optimal transport is introduced, and for several cost classes including the rectangular cost, the unique minimizer is a new diamond-shaped coupling rather than the usual comonotone or antimonotone couplings.

citing papers explorer

Showing 1 of 1 citing paper.

  • Quadratic-form Optimal Transport math.PR · 2025-01-08 · accept · none · ref 2000 · internal anchor

    Quadratic-form optimal transport is introduced, and for several cost classes including the rectangular cost, the unique minimizer is a new diamond-shaped coupling rather than the usual comonotone or antimonotone couplings.