147 citations · 439 across the 10 of their papers we have counts for
5 papers · 1 filter
Do Neural Optimal Transport Solvers Work? A Continuous Wasserstein-2 Benchmark
Alexander Korotin, Lingxiao Li, Aude Genevay +3
Despite the recent popularity of neural network-based solvers for optimal transport (OT), there is no standard quantitative way to evaluate their performance. In this paper, we add…
Large-Scale Wasserstein Gradient Flows
Petr Mokrov, Alexander Korotin, Lingxiao Li +3
Wasserstein gradient flows provide a powerful means of understanding and solving many diffusion equations. Specifically, Fokker-Planck equations, which model the diffusion of proba…
Improving Approximate Optimal Transport Distances using Quantization
Gaspard Beugnot, Aude Genevay, Kristjan Greenewald +1
Optimal transport (OT) is a popular tool in machine learning to compare probability measures geometrically, but it comes with substantial computational burden. Linear programming a…
Continuous Regularized Wasserstein Barycenters
Lingxiao Li, Aude Genevay, Mikhail Yurochkin +1
Wasserstein barycenters provide a geometrically meaningful way to aggregate probability distributions, built on the theory of optimal transport. They are difficult to compute in pr…
Differentiable Deep Clustering with Cluster Size Constraints
Aude Genevay, Gabriel Dulac-Arnold, Jean-Philippe Vert
Clustering is a fundamental unsupervised learning approach. Many clustering algorithms -- such as -means -- rely on the euclidean distance as a similarity measure, which is ofte…