English
Related papers

Related papers: Straight-Through Estimator as Projected Wasserstei…

200 papers

Recently used in various machine learning contexts, the Gromov-Wasserstein distance (GW) allows for comparing distributions whose supports do not necessarily lie in the same metric space. However, this Optimal Transport (OT) distance…

Machine Learning · Statistics 2022-10-21 Titouan Vayer , Rémi Flamary , Romain Tavenard , Laetitia Chapel , Nicolas Courty

These notes aim to shed light on the recently proposed structured projected intermediate gradient optimization technique (SPIGOT, Peng et al., 2018). SPIGOT is a variant of the straight-through estimator (Bengio et al., 2013) which bypasses…

Machine Learning · Computer Science 2019-07-25 André F. T. Martins , Vlad Niculae

Training activation quantized neural networks involves minimizing a piecewise constant function whose gradient vanishes almost everywhere, which is undesirable for the standard back-propagation or chain rule. An empirical way around this…

Machine Learning · Computer Science 2019-09-26 Penghang Yin , Jiancheng Lyu , Shuai Zhang , Stanley Osher , Yingyong Qi , Jack Xin

In the field of modern high-energy physics research, there is a growing emphasis on utilizing deep learning techniques to optimize event simulation, thereby expanding the statistical sample size for more accurate physical analysis.…

Computational Physics · Physics 2025-06-16 Chu-Cheng Pan , Xiang Dong , Yu-Chang Sun , Ao-Yan Cheng , Ao-Bo Wang , Yu-Xuan Hu , Hao Cai

We give quantitative estimates for the rate of convergence of Riemannian stochastic gradient descent (RSGD) to Riemannian gradient flow and to a diffusion process, the so-called Riemannian stochastic modified flow (RSMF). Using tools from…

Machine Learning · Computer Science 2025-03-10 Benjamin Gess , Sebastian Kassing , Nimit Rana

Motivated by the omnipresence of extreme value distributions in limit theorems involving extremes of random processes, we adapt Stein's method to include these laws as possible target distributions. We do so by using the generator approach…

Probability · Mathematics 2025-07-02 Bruno Costacèque , Laurent Decreusefond

This article compares the distributions of integer-valued random variables and Poisson random variables. It considers the total variation and the Wasserstein distance and provides, in particular, explicit bounds on the pointwise difference…

Probability · Mathematics 2021-04-07 Federico Pianoforte , Matthias Schulte

We present a novel class of projected methods, to perform statistical analysis on a data set of probability distributions on the real line, with the 2-Wasserstein metric. We focus in particular on Principal Component Analysis (PCA) and…

Methodology · Statistics 2021-11-30 Matteo Pegoraro , Mario Beraha

Score-based generative modeling with probability flow ordinary differential equations (ODEs) has achieved remarkable success in a variety of applications. While various fast ODE-based samplers have been proposed in the literature and…

Machine Learning · Statistics 2025-08-12 Xuefeng Gao , Lingjiong Zhu

We study distribution-on-distribution regression problems in which a response distribution depends on multiple distributional predictors. Such settings arise naturally in applications where the outcome distribution is driven by several…

Methodology · Statistics 2026-01-08 Yuanying Chen , Tongyu Li , Yang Bai , Zhenhua Lin

The sliced Wasserstein (SW) distance has been widely recognized as a statistically effective and computationally efficient metric between two probability measures. A key component of the SW distance is the slicing distribution. There are…

Machine Learning · Statistics 2024-01-02 Khai Nguyen , Nhat Ho

We present a simple approach to study the one-dimensional pressureless Euler system via adhesion dynamics in the Wasserstein space of probability measures with finite quadratic moments. Starting from a discrete system of a finite number of…

Analysis of PDEs · Mathematics 2014-09-16 Luca Natile , Giuseppe Savaré

Squared Wasserstein distance is a frequently used tool to measure discrepancy between probability distributions. This distance is typically computed between empirical measures of size $n$ from two underlying random samples. Unfortunately,…

Machine Learning · Statistics 2026-05-20 Peter Matthew Jacobs , Jeff M. Phillips

Stein operators are differential operators which arise within the so-called Stein's method for stochastic approximation. We propose a new mechanism for constructing such operators for arbitrary (continuous or discrete) parametric…

Probability · Mathematics 2013-05-23 Christophe Ley , Yvik Swan

This paper presents a Wasserstein attraction approach for solving dynamic mass transport problems over networks. In the transport problem over networks, we start with a distribution over the set of nodes that needs to be "transported" to a…

Optimization and Control · Mathematics 2022-04-28 Ferran Arqué , César A. Uribe , Carlos Ocampo-Martinez

The goal of scenario reduction is to approximate a given discrete distribution with another discrete distribution that has fewer atoms. We distinguish continuous scenario reduction, where the new atoms may be chosen freely, and discrete…

Optimization and Control · Mathematics 2017-01-17 Napat Rujeerapaiboon , Kilian Schindler , Daniel Kuhn , Wolfram Wiesemann

In this paper, we investigate the properties of the Sliced Wasserstein Distance (SW) when employed as an objective functional. The SW metric has gained significant interest in the optimal transport and machine learning literature, due to…

Machine Learning · Statistics 2025-08-21 Christophe Vauthier , Anna Korba , Quentin Mérigot

We develop in this paper a new regularized flow dynamic approach to construct efficient numerical schemes for Wasserstein gradient flows in Lagrangian coordinates. Instead of approximating the Wasserstein distance which needs to solve…

Numerical Analysis · Mathematics 2024-06-24 Qing Cheng , Qianqian Liu , Wenbin Chen , Jie Shen

In this paper we propose tight upper and lower bounds for the Wasserstein distance between any two {{univariate continuous distributions}} with probability densities $p_1$ and $p_2$ having nested supports. These explicit bounds are…

Probability · Mathematics 2015-10-21 Christophe Ley , Gesine Reinert , Yvik Swan

We derive quantitative bounds on the rate of convergence in $L^1$ Wasserstein distance of general M-estimators, with an almost sharp (up to a logarithmic term) behavior in the number of observations. We focus on situations where the…

Statistics Theory · Mathematics 2021-11-19 François Bachoc , Max Fathi