Computational optimal transport: Complexity by accelerated gradient descent is better than by Sinkhorn's algorithm
P Dvurechensky, A Gasnikov… - … conference on machine …, 2018 - proceedings.mlr.press
We analyze two algorithms for approximating the general optimal transport (OT) distance
between two discrete distributions of size $ n $, up to accuracy $\varepsilon $. For the first …
between two discrete distributions of size $ n $, up to accuracy $\varepsilon $. For the first …
On efficient optimal transport: An analysis of greedy and accelerated mirror descent algorithms
We provide theoretical analyses for two algorithms that solve the regularized optimal
transport (OT) problem between two discrete probability measures with at most $ n $ atoms …
transport (OT) problem between two discrete probability measures with at most $ n $ atoms …
On the complexity of approximating Wasserstein barycenters
We study the complexity of approximating the Wasserstein barycenter of $ m $ discrete
measures, or histograms of size $ n $, by contrasting two alternative approaches that use …
measures, or histograms of size $ n $, by contrasting two alternative approaches that use …
A direct tilde {O}(1/epsilon) iteration parallel algorithm for optimal transport
Optimal transportation, or computing the Wasserstein or``earth mover's''distance between
two $ n $-dimensional distributions, is a fundamental primitive which arises in many learning …
two $ n $-dimensional distributions, is a fundamental primitive which arises in many learning …
Multi-target association algorithm of AIS-radar tracks using graph matching-based deep neural network
Y Yang, F Yang, L Sun, T Xiang, P Lv - Ocean Engineering, 2022 - Elsevier
Abstract Automatic Identification System (AIS) and radar track association is a challenging
subject in dense scenes in which there are some undesirable factors, such as multiple …
subject in dense scenes in which there are some undesirable factors, such as multiple …
Towards optimal running times for optimal transport
In this work, we provide faster algorithms for approximating the optimal transport distance,
eg earth mover's distance, between two discrete probability distributions $\mu,\nu\in\Delta^ n …
eg earth mover's distance, between two discrete probability distributions $\mu,\nu\in\Delta^ n …
LinSATNet: the positive linear satisfiability neural networks
Encoding constraints into neural networks is attractive. This paper studies how to introduce
the popular positive linear satisfiability to neural networks. We propose the first differentiable …
the popular positive linear satisfiability to neural networks. We propose the first differentiable …
Approximating optimal transport with linear programs
K Quanrud - arXiv preprint arXiv:1810.05957, 2018 - arxiv.org
arXiv:1810.05957v2 [cs.DS] 21 Oct 2018 Page 1 arXiv:1810.05957v2 [cs.DS] 21 Oct 2018
Approximating optimal transport with linear programs Kent Quanrud∗ October 23, 2018 Abstract …
Approximating optimal transport with linear programs Kent Quanrud∗ October 23, 2018 Abstract …
Biwhitening reveals the rank of a count matrix
Estimating the rank of a corrupted data matrix is an important task in data analysis, most
notably for choosing the number of components in principal component analysis. Significant …
notably for choosing the number of components in principal component analysis. Significant …
A gradient descent perspective on Sinkhorn
F Léger - Applied Mathematics & Optimization, 2021 - Springer
We present a new perspective on the popular Sinkhorn algorithm, showing that it can be
seen as a Bregman gradient descent (mirror descent) of a relative entropy (Kullback–Leibler …
seen as a Bregman gradient descent (mirror descent) of a relative entropy (Kullback–Leibler …