arXiv research

The Sinkhorn flow converges to a Wasserstein mirror gradient flow from the Sinkhorn algorithm.

Continuous-time Sinkhorn flow generalizes and unifies existing dynamics.

The Sinkhorn flow is a gradient flow in a nonlocal Wasserstein geometry.

Large Sinkhorn couplings improve flow models in data generation tasks.

A new associative memory uses Sinkhorn divergence for efficient pattern retrieval.

A new gradient flow framework for distributionally robust optimization.

A new algorithm estimates aggregate marginals from noisy data in an online manner.

New discretization scheme for Wasserstein gradient flows using Schrödinger bridges.

Analyzed a generative model framework through Wasserstein Gradient Flow.

W-Flow generates images in one step, faster and better than multi-step methods.

Improved online Sinkhorn algorithm for large-scale data processing.

The Sinkhorn-Knopp derivatives converge with linear rate.

Paper solves barycenter of probability distributions using Sinkhorn divergence.

We introduce in this paper a novel strategy for efficiently approximating the Sinkhorn distance between two discrete measures. After identifying neglectable components of the dual solution of the regularized Sinkhorn problem, we propose to screen those components by directly setting them at that value before entering t…

Survey of Sinkhorn algorithm for optimal transport, emphasizing its geometric origins.

SNS accelerates Sinkhorn algorithm with sparse Newton iterations.

New stability theory for Sinkhorn semigroups with explicit decay rates.

The Sinkhorn "distance", a variant of the Wasserstein distance with entropic regularization, is an increasingly popular tool in machine learning and statistical inference. However, the time and memory requirements of standard algorithms for computing this distance grow quadratically with the size of the data, making th…

A new algorithm for learning shallow neural networks with infinite width.

This work studies the statistical performance of Sinkhorn iterations in estimating Schrödinger bridges.

This paper tackles Sinkhorn DRO by reformulating it as a bilevel program and proposes sampling-based algorithms.

Paper uses Sinkhorn distances to improve imitation learning effectiveness.

Optimizes distributions robustly with Sinkhorn distance.

We provide a computational complexity analysis for the Sinkhorn algorithm that solves the entropic regularized Unbalanced Optimal Transport (UOT) problem between two measures of possibly different masses with at most $n$ components. We show that the complexity of the Sinkhorn algorithm for finding an $\varepsilon$-appr…

This paper refines the Gaussian Sinkhorn algorithm for general multivariate models.

We study the complexity of approximating the multimarginal optimal transport (MOT) distance, a generalization of the classical optimal transport distance, considered here between $m$ discrete probability distributions supported each on $n$ support points. First, we show that the standard linear programming (LP) represe…

OTSeg uses multi-prompt Sinkhorn attention to improve zero-shot semantic segmentation.

Develops a new algorithm to calibrate signed datasets to specified marginals.

A new algorithm for training generative models using Sinkhorn divergence.

Reflective Hamiltonian Monte Carlo struggles with high-dimensional sampling.

Computing optimal transport distances such as the earth mover's distance is a fundamental problem in machine learning, statistics, and computer vision. Despite the recent introduction of several algorithms with good empirical performance, it is unknown whether general optimal transport distances can be approximated in …

We present a novel algorithm to estimate the barycenter of arbitrary probability distributions with respect to the Sinkhorn divergence. Based on a Frank-Wolfe optimization strategy, our approach proceeds by populating the support of the barycenter incrementally, without requiring any pre-allocation. We consider discret…

Study convergence and approximations of entropic regularized Wasserstein distances for Gaussian and RKHS measures.

Paper proposes a robust hypothesis testing method using Sinkhorn distance.

Paper proposes SinkhornDRL for distributional RL using Sinkhorn divergence and regularized Wasserstein loss.

Optimal transport with $f$-divergence regularization using generalized Sinkhorn algorithm.

A new method for faster estimation of Wasserstein distance using Sinkhorn divergence.

New methods improve stability of Sinkhorn algorithm in machine learning.

The paper analyzes stability and convergence rates of entropic and Sinkhorn potentials.

Paper proves generalized Talagrand inequality for Sinkhorn distance.

A new method for flow matching reduces computational costs and improves performance.

End-to-end Sinkhorn Autoencoder reduces data simulation time with noise generation.

New initialization methods speed up Sinkhorn algorithm for OT problems.

Extends geostatistical simulation method to handle multiple variables and large grids.

Paper analyzes convergence of Sinkhorn algorithm for discrete probability measures on torus.

A new method reduces the computational cost of Sinkhorn algorithm for OT and UOT problems.

We present several new complexity results for the entropic regularized algorithms that approximately solve the optimal transport (OT) problem between two discrete probability measures with at most $n$ atoms. First, we improve the complexity bound of a greedy variant of Sinkhorn, known as \textit{Greenkhorn}, from $\wid…

New framework for robust hypothesis testing using Sinkhorn uncertainty sets.