Faster Wasserstein distance estimation with the Sinkhorn divergence
The squared Wasserstein distance is a natural quantity to compare probability distributions
in a non-parametric setting. This quantity is usually estimated with the plug-in estimator …
in a non-parametric setting. This quantity is usually estimated with the plug-in estimator …
Bipartite matching in nearly-linear time on moderately dense graphs
We present an ̃O(m+n^1.5)-time randomized algorithm for maximum cardinality bipartite
matching and related problems (eg transshipment, negative-weight shortest paths, and …
matching and related problems (eg transshipment, negative-weight shortest paths, and …
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 …
Fliptest: fairness testing via optimal transport
We present FlipTest, a black-box technique for uncovering discrimination in classifiers.
FlipTest is motivated by the intuitive question: had an individual been of a different protected …
FlipTest is motivated by the intuitive question: had an individual been of a different protected …
Massively scalable Sinkhorn distances via the Nyström method
The Sinkhorn" distance," a variant of the Wasserstein distance with entropic regularization, is
an increasingly popular tool in machine learning and statistical inference. However, the time …
an increasingly popular tool in machine learning and statistical inference. However, the time …
On the complexity of approximating multimarginal optimal transport
We study the complexity of approximating the multimarginal optimal transport (MOT)
distance, a generalization of the classical optimal transport distance, considered here …
distance, a generalization of the classical optimal transport distance, considered here …
Fixed-support Wasserstein barycenters: Computational hardness and fast algorithm
We study the fixed-support Wasserstein barycenter problem (FS-WBP), which consists in
computing the Wasserstein barycenter of $ m $ discrete probability measures supported on …
computing the Wasserstein barycenter of $ m $ discrete probability measures supported on …
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 …
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 …
[HTML][HTML] Polynomial-time algorithms for multimarginal optimal transport problems with structure
JM Altschuler, E Boix-Adsera - Mathematical Programming, 2023 - Springer
Abstract Multimarginal Optimal Transport (MOT) has attracted significant interest due to
applications in machine learning, statistics, and the sciences. However, in most applications …
applications in machine learning, statistics, and the sciences. However, in most applications …