中文
相关论文

相关论文: A novel notion of barycenter for probability distr…

200 篇论文

Worst-case generation plays a critical role in evaluating robustness and stress-testing systems under distribution shifts, in applications ranging from machine learning models to power grids and medical prediction systems. We develop a…

机器学习 · 统计学 2025-12-10 Xiuyuan Cheng , Yao Xie , Linglingzhi Zhu , Yunqin Zhu

Discrete barycenters are the optimal solutions to mass transport problems for a set of discrete measures. Such transport problems arise in many applications of operations research and statistics. The best known algorithms for exact…

最优化与控制 · 数学 2019-04-24 Steffen Borgwardt , Stephan Patterson

We investigate barycenters of probability measures on Gromov hyperbolic spaces, toward development of convex optimization in this class of metric spaces. We establish a contraction property (the Wasserstein distance between probability…

度量几何 · 数学 2024-06-18 Shin-ichi Ohta

The theory of weak optimal transport (WOT), introduced by [Gozlan et al., 2017], generalizes the classic Monge-Kantorovich framework by allowing the transport cost between one point and the points it is matched with to be nonlinear. In the…

机器学习 · 统计学 2022-05-24 François-Pierre Paty , Philippe Choné , Francis Kramarz

In this work we consider regularized Wasserstein barycenters (average in Wasserstein distance) in Fourier basis. We prove that random Fourier parameters of the barycenter converge to some Gaussian random vector by distribution. The…

统计理论 · 数学 2021-09-21 Nazar Buzun

Due to its invariance to rigid transformations such as rotations and reflections, Procrustes-Wasserstein (PW) was introduced in the literature as an optimal transport (OT) distance, alternative to Wasserstein and more suited to tasks such…

机器学习 · 统计学 2025-07-02 Davide Adamo , Marco Corneli , Manon Vuillien , Emmanuelle Vila

We commonly encounter the problem of identifying an optimally weight adjusted version of the empirical distribution of observed data, adhering to predefined constraints on the weights. Such constraints often manifest as restrictions on the…

机器学习 · 统计学 2024-01-17 Abhisek Chakraborty , Anirban Bhattacharya , Debdeep Pati

Suppose we are given two metric spaces and a family of continuous transformations from one to the other. Given a probability distribution on each of these two spaces - namely the source and the target measures - the Wasserstein alignment…

概率论 · 数学 2025-03-11 Soumik Pal , Bodhisattva Sen , Ting-Kam Leonard Wong

Clustering is an important exploratory data analysis technique to group objects based on their similarity. The widely used $K$-means clustering method relies on some notion of distance to partition data into a fewer number of groups. In the…

机器学习 · 统计学 2022-10-14 Yubo Zhuang , Xiaohui Chen , Yun Yang

Wasserstein barycenters and variance-like criteria based on the Wasserstein distance are used in many problems to analyze the homogeneity of collections of distributions and structural relationships between the observations. We propose the…

We present a new method to propagate lower bounds on conditional probability distributions in conventional Bayesian networks. Our method guarantees to provide outer approximations of the exact lower bounds. A key advantage is that we can…

人工智能 · 计算机科学 2012-05-14 Daniel Andrade , Bernhard Sick

This paper considers the problem of regression over distributions, which is becoming increasingly important in machine learning. Existing approaches often ignore the geometry of the probability space or are computationally expensive. To…

机器学习 · 计算机科学 2025-10-31 Maksim Maslov , Alexander Kugaevskikh , Matthew Ivanov

We formulate and solve a regression problem with time-stamped distributional data. Distributions are considered as points in the Wasserstein space of probability measures, metrized by the 2-Wasserstein metric, and may represent images,…

系统与控制 · 电气工程与系统科学 2021-06-30 Amirhossein Karimi , Tryphon T. Georgiou

We consider the rate-distortion function for lossy source compression, as well as the channel capacity for error correction, through the lens of distributional robustness. We assume that the distribution of the source or of the additive…

信息论 · 计算机科学 2024-05-14 Vikrant Malik , Taylan Kargin , Victoria Kostina , Babak Hassibi

We provide theoretical complexity analysis for new algorithms to compute the optimal transport (OT) distance between two discrete probability distributions, and demonstrate their favorable practical performance over state-of-art primal-dual…

数据结构与算法 · 计算机科学 2020-06-16 Wenshuo Guo , Nhat Ho , Michael I. Jordan

Peak counts have been shown to be an excellent tool to extract the non-Gaussian part of the weak lensing signal. Recently, we developped a fast stochastic forward model to predict weak-lensing peak counts. Our model is able to reconstruct…

宇宙学与河外天体物理 · 物理学 2015-11-16 Chieh-An Lin , Martin Kilbinger

In this paper, based on the Fr{\'e}chet mean, we define a notion of barycenter corresponding to a usual notion of statistical mean. We prove the existence of Wasserstein barycenters of random distributions defined on a geodesic space (E,…

统计理论 · 数学 2016-02-15 Thibaut Le Gouic , Jean-Michel Loubes

Recently, it has been shown that it is possible to reconstruct the projected mass distribution of a cluster from weak lensing provided that both the geometry of the universe and the probability distribution of galaxy redshifts are known;…

天体物理学 · 物理学 2007-05-23 Marco Lombardi , Giuseppe Bertin

Variational problems that involve Wasserstein distances and more generally optimal transport (OT) theory are playing an increasingly important role in data sciences. Such problems can be used to form an examplar measure out of various…

机器学习 · 计算机科学 2018-11-15 Marco Cuturi , Gabriel Peyré

The increasing availability of granular and big data on various objects of interest has made it necessary to develop methods for condensing this information into a representative and intelligible map. Financial regulation is a field that…

机器学习 · 统计学 2025-07-08 Lorenz Riess , Mathias Beiglböck , Johannes Temme , Andreas Wolf , Julio Backhoff