Results 31 to 40 of about 2,509,053 (235)
A Distributionally Robust Approach to Regret Optimal Control using the Wasserstein Distance [PDF]
IEEE Conference on Decision and Control, 2023 This paper proposes a distributionally robust approach to regret optimal control of discrete-time linear dynam-ical systems with quadratic costs subject to a stochastic additive disturbance on the state process. The underlying probability distribution of
Shuhao Yan, Feras Al Taha, E. Bitar
semanticscholar +1 more source
IEEE transactions on neural systems and rehabilitation engineering, 2023 Motor Imagery (MI) paradigm is critical in neural rehabilitation and gaming. Advances in brain-computer interface (BCI) technology have facilitated the detection of MI from electroencephalogram (EEG).
Qingshan She +5 more
semanticscholar +1 more source
Entropy-Regularized Optimal Transport on Multivariate Normal and q-normal Distributions
Entropy, 2021 The distance and divergence of the probability measures play a central role in statistics, machine learning, and many other related fields. The Wasserstein distance has received much attention in recent years because of its distinctions from other ...
Qijun Tong, Kei Kobayashi
doaj +1 more source
Earth mover’s distance as a measure of CP violation
Journal of High Energy Physics, 2023 We introduce a new unbinned two sample test statistic sensitive to CP violation utilizing the optimal transport plan associated with the Wasserstein (earth mover’s) distance.
Adam Davis +3 more
doaj +1 more source
On the rate of convergence in Wasserstein distance of the empirical measure [PDF]
Probability theory and related fields, 2013 Let μN\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\mu _N$$\end ...
N. Fournier, A. Guillin
semanticscholar +1 more source
Donsker’s theorem in Wasserstein-1 distance [PDF]
Electronic Communications in Probability, 2020 We compute the Wassertein-1 (or Kolmogorov-Rubinstein) distance between a random walk in $R^d$ and the Brownian motion. The proof is based on a new estimate of the Lipschitz modulus of the solution of the Stein's equation. As an application, we can evaluate the rate of convergence towards the local time at 0 of the Brownian motion.
Coutin, Laure, Decreusefond, Laurent
openaire +4 more sources
Multimedia Analysis and Fusion via Wasserstein Barycenter
International Journal of Networked and Distributed Computing (IJNDC), 2020 Optimal transport distance, otherwise known as Wasserstein distance, recently has attracted attention in music signal processing and machine learning as powerful discrepancy measures for probability distributions.
Cong Jin +7 more
doaj +1 more source
Distributionally Robust Stochastic Optimization with Wasserstein Distance [PDF]
Mathematics of Operations Research, 2016 Distributionally robust stochastic optimization (DRSO) is an approach to optimization under uncertainty in which, instead of assuming that there is a known true underlying probability distribution, one hedges against a chosen set of distributions.
Rui Gao, A. Kleywegt
semanticscholar +1 more source
DeepWSD: Projecting Degradations in Perceptual Space to Wasserstein Distance in Deep Feature Space [PDF]
ACM Multimedia, 2022 Existing deep learning-based full-reference IQA (FR-IQA) models usually predict the image quality in a deterministic way by explicitly comparing the features, gauging how severely distorted an image is by how far the corresponding feature lies from the ...
Xigran Liao +5 more
semanticscholar +1 more source
The Ultrametric Gromov–Wasserstein Distance
Discrete & Computational Geometry, 2023 In this paper, we investigate compact ultrametric measure spaces which form a subset $\mathcal{U}^w$ of the collection of all metric measure spaces $\mathcal{M}^w$. Similar as for the ultrametric Gromov-Hausdorff distance on the collection of ultrametric spaces $\mathcal{U}$, we define ultrametric versions of two metrics on $\mathcal{U}^w$, namely of ...
Facundo Mémoli +3 more
openaire +4 more sources