Pith. sign in

$L^2$ over Wasserstein: Statistical Analysis for Optimal Transport

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

1 Pith paper citing it
abstract

Optimal transport provides an inherently geometric and highly structured framework for studying spaces of probability measures, supplying a rich theoretical toolkit for contemporary statistics, machine learning, and generative modelling. In applications, however, the measures of interest are almost never known precisely, calling for a theory of optimal transport that accounts for statistical uncertainty. We construct such a framework, lifting the classical theory to the setting of random probability measures. We introduce the $L^2$ over Wasserstein space establishing that it inherits the formal Riemannian structure of the Wasserstein space by characterising distances and geodesic geometry. The structure induces random flows with Wasserstein gradient flow sample paths, making it the natural extension of the Wasserstein space which allows for random gradient flow dynamics. We ensemble statistical convergence results of the optimal transport machinery using the empirical measure within the $L^2$ over Wasserstein framework. Moreover, in the setting of Bayesian non-parametrics, we refine Schwartz's consistency theorem to the Wasserstein topology and deduce posterior convergence of the same machinery in the $L^2$ over Wasserstein space. We demonstrate that the growing theory of random token sampling for transformer models using self-attention flow paths can be embedded into the our framework. The results provide a unified treatment of random optimal transport and its consequences for principled inference and generative modelling under the statistical uncertainty of random sampling.

fields

cs.LG 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Conditional Random Ordered Transport Spaces

cs.LG · 2026-06-06 · unverdicted · novelty 8.0

Introduces CROTS, a class of random measure spaces with Wasserstein ambient metric, closed stochastic order, hard/soft ordered transport discrepancies, and conditional risk for evidence-constrained learning.

citing papers explorer

Showing 1 of 1 citing paper.

  • Conditional Random Ordered Transport Spaces cs.LG · 2026-06-06 · unverdicted · none · ref 17 · internal anchor

    Introduces CROTS, a class of random measure spaces with Wasserstein ambient metric, closed stochastic order, hard/soft ordered transport discrepancies, and conditional risk for evidence-constrained learning.