arXiv research

Paper improves likelihood estimation for discrete distributions.

Improved online Sinkhorn algorithm for large-scale data processing.

Continuous-time Sinkhorn flow generalizes and unifies existing dynamics.

The Sinkhorn-Knopp derivatives converge with linear rate.

Paper solves barycenter of probability distributions using Sinkhorn divergence.

We introduce the notion of regular finite decomposition complexity of a metric family. This generalizes Gromov's finite asymptotic dimension and is motivated by the concept of finite decomposition complexity (FDC) due to Guentner, Tessera and Yu. Regular finite decomposition complexity implies FDC and has all the perma…

Improved Sinkhorn algorithm for UOT with near-linear complexity.

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.

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

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…

There are two schools of thought regarding market impact modeling. On the one hand, seminal papers by Almgren and Chriss introduced a decomposition between a permanent market impact and a temporary (or instantaneous) market impact. This decomposition is used by most practitioners in execution models. On the other hand,…

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.

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

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

The paper analyzes optimal liquidation strategies for cryptocurrencies considering both temporary and permanent price impacts.

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.

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.

One of the fundamental problems in supervised classification and in machine learning in general, is the modelling of non-parametric invariances that exist in data. Most prior art has focused on enforcing priors in the form of invariances to parametric nuisance transformations that are expected to be present in data. Le…

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.

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.

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

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.

Stochastic discount factor (SDF) processes in dynamic economies admit a permanent-transitory decomposition in which the permanent component characterizes pricing over long investment horizons. This paper introduces an empirical framework to analyze the permanent-transitory decomposition of SDF processes. Specifically, …

Permutations and matchings are core building blocks in a variety of latent variable models, as they allow us to align, canonicalize, and sort data. Learning in such models is difficult, however, because exact marginalization over these combinatorial objects is intractable. In response, this paper introduces a collectio…

We study the relaxation dynamics of the bid-ask spread and of the midprice after a sudden, large variation of the spread, corresponding to a temporary crisis of liquidity in a double auction financial market. We find that the spread decays very slowly to its normal value as a consequence of the strategic limit order pl…

New algorithm solves Schrödinger bridge problem with mismatched channels.

Estimating mutual information is an important statistics and machine learning problem. To estimate the mutual information from data, a common practice is preparing a set of paired samples $\{(\mathbf{x}_i,\mathbf{y}_i)\}_{i=1}^n \stackrel{\mathrm{i.i.d.}}{\sim} p(\mathbf{x},\mathbf{y})$. However, in many situations, it…