English
Related papers

Related papers: From Generalisation Error to Transportation-cost I…

200 papers

We derive upper bounds on the generalization error of learning algorithms based on their \emph{algorithmic transport cost}: the expected Wasserstein distance between the output hypothesis and the output hypothesis conditioned on an input…

Machine Learning · Statistics 2018-11-09 Jingwei Zhang , Tongliang Liu , Dacheng Tao

We relate transport-entropy inequalities to the study of critical points of functionals defined on the space of probability measures. This approach leads in particular to a new proof of a result by Otto and Villani [43] showing that the…

Probability · Mathematics 2016-04-27 Joaquin Fontbona , Nathael Gozlan , Jean-Francois Jabir

The duality theory of the Monge--Kantorovich transport problem is analyzed in a general setting. The spaces $X, Y$ are assumed to be polish and equipped with Borel probability measures $\mu$ and $\nu$. The transport cost function $c:X\times…

Optimization and Control · Mathematics 2010-09-07 Mathias Beiglboeck , Christian Leonard , Walter Schachermayer

We study Bregman divergences in probability density space embedded with the $L^2$-Wasserstein metric. Several properties and dualities of transport Bregman divergences are provided. In particular, we derive the transport Kullback-Leibler…

Information Theory · Computer Science 2025-04-08 Wuchen Li

The article builds on several recent advances in the Monge-Kantorovich theory of mass transport which have -- among other things -- led to new and quite natural proofs for a wide range of geometric inequalities such as the ones formulated…

Analysis of PDEs · Mathematics 2007-05-23 M. Agueh , N. Ghoussoub , X. Kang

We study concentration properties for laws of non-linear Gaussian functionals on metric spaces. Our focus lies on measures with non-Gaussian tail behaviour which are beyond the reach of Talagrand's classical Transportation-Cost Inequalities…

Probability · Mathematics 2023-10-12 Ioannis Gasteratos , Antoine Jacquier

Expectation Propagation is a very popular algorithm for variational inference, but comes with few theoretical guarantees. In this article, we prove that the approximation errors made by EP can be bounded. Our bounds have an asymptotic…

Computation · Statistics 2016-01-12 Guillaume P Dehaene , Simon Barthelmé

Optimal transport has emerged as a fundamental methodology with applications spanning multiple research areas in recent years. However, the convergence rate of the empirical estimator to its population counterpart suffers from the curse of…

Statistics Theory · Mathematics 2025-10-06 Jiaping Yang , Yunxin Zhang

The dual attainment of the Monge--Kantorovich transport problem is analyzed in a general setting. The spaces $X, Y$ are assumed to be polish and equipped with Borel probability measures $\mu$ and $\nu$. The transport cost function $c:\XY…

Optimization and Control · Mathematics 2020-07-17 Mathias Beiglböck , Christian Léonard , Walter Schachermayer

The de cit in the logarithmic Sobolev inequality for the Gaussian measure is considered and estimated by means of transport and information-theoretic distances.

Probability · Mathematics 2014-08-12 Sergey Bobkov , Nathael Gozlan , Cyril Roberto , Paul-Marie Samson

Many causal and structural parameters in economics can be identified and estimated by computing the value of an optimization program over all distributions consistent with the model and the data. Existing tools apply when the data is…

Econometrics · Economics 2025-07-31 Andrei Voronin

While the expected calibration error (ECE), which employs binning, is widely adopted to evaluate the calibration performance of machine learning models, theoretical understanding of its estimation bias is limited. In this paper, we present…

Machine Learning · Computer Science 2025-05-27 Futoshi Futami , Masahiro Fujisawa

Equilibrium properties in statistical physics are obtained by computing averages with respect to Boltzmann-Gibbs measures, sampled in practice using ergodic dynamics such as the Langevin dynamics. Some quantities however cannot be computed…

Numerical Analysis · Mathematics 2023-01-02 Gabriel Stoltz

A probabilistic method for solving the Monge-Kantorovich mass transport problem on $R^d$ is introduced. A system of empirical measures of independent particles is built in such a way that it obeys a doubly indexed large deviation principle…

Probability · Mathematics 2007-10-09 Christian Léonard

Locational measures of accessibility are widely used in urban and transportation planning to understand the impact of the transportation system on influencing people's access to places. However, there is a considerable lack of measurement…

Econometrics · Economics 2024-04-09 Rajat Verma , Mithun Debnath , Shagun Mittal , Satish V. Ukkusuri

We introduce a general notion of transport cost that encompasses many costs used in the literature (including the classical one and weak transport costs introduced by Talagrand and Marton in the 90's), and prove a Kantorovich type duality…

Probability · Mathematics 2015-12-25 Nathael Gozlan , Cyril Roberto , Paul-Marie Samson , Prasad Tetali

The families of $f$-divergences (e.g. the Kullback-Leibler divergence) and Integral Probability Metrics (e.g. total variation distance or maximum mean discrepancies) are widely used to quantify the similarity between probability…

Statistics Theory · Mathematics 2021-06-08 Rohit Agrawal , Thibaut Horel

We consider Monge-Kantorovich optimal transport problems on $\mathbb{R}^d$, $d\ge 1$, with a convex cost function given by the cumulant generating function of a probability measure. Examples include the Wasserstein-2 transport whose cost…

Probability · Mathematics 2017-08-29 Soumik Pal

Generalization methods offer a powerful solution to one of the key drawbacks of randomized controlled trials (RCTs): their limited representativeness. By enabling the transport of treatment effect estimates to target populations subject to…

Methodology · Statistics 2025-05-20 Ahmed Boughdiri , Clément Berenfeld , Julie Josse , Erwan Scornet

This article presents a general approximation-theoretic framework to analyze measure transport algorithms for probabilistic modeling. A primary motivating application for such algorithms is sampling -- a central task in statistical…

Numerical Analysis · Mathematics 2024-09-19 Ricardo Baptista , Bamdad Hosseini , Nikola B. Kovachki , Youssef M. Marzouk , Amir Sagiv