Wasserstein distributionally robust optimization: Theory and applications in machine learning
Many decision problems in science, engineering, and economics are affected by uncertain
parameters whose distribution is only indirectly observable through samples. The goal of …
parameters whose distribution is only indirectly observable through samples. The goal of …
Pot: Python optimal transport
Optimal transport has recently been reintroduced to the machine learning community thanks
in part to novel efficient optimization procedures allowing for medium to large scale …
in part to novel efficient optimization procedures allowing for medium to large scale …
Near-linear time approximation algorithms for optimal transport via Sinkhorn iteration
J Altschuler, J Niles-Weed… - Advances in neural …, 2017 - proceedings.neurips.cc
Computing optimal transport distances such as the earth mover's distance is a fundamental
problem in machine learning, statistics, and computer vision. Despite the recent introduction …
problem in machine learning, statistics, and computer vision. Despite the recent introduction …
Projection‐based techniques for high‐dimensional optimal transport problems
Optimal transport (OT) methods seek a transformation map (or plan) between two probability
measures, such that the transformation has the minimum transportation cost. Such a …
measures, such that the transformation has the minimum transportation cost. Such a …
Unsupervised alignment of embeddings with wasserstein procrustes
We consider the task of aligning two sets of points in high dimension, which has many
applications in natural language processing and computer vision. As an example, it was …
applications in natural language processing and computer vision. As an example, it was …
Differentiable particle filtering via entropy-regularized optimal transport
A Corenflos, J Thornton… - International …, 2021 - proceedings.mlr.press
Particle Filtering (PF) methods are an established class of procedures for performing
inference in non-linear state-space models. Resampling is a key ingredient of PF necessary …
inference in non-linear state-space models. Resampling is a key ingredient of PF necessary …
Differentiable ranking and sorting using optimal transport
Sorting is used pervasively in machine learning, either to define elementary algorithms, such
as $ k $-nearest neighbors ($ k $-NN) rules, or to define test-time metrics, such as top-$ k …
as $ k $-nearest neighbors ($ k $-NN) rules, or to define test-time metrics, such as top-$ k …
Subspace robust Wasserstein distances
Making sense of Wasserstein distances between discrete measures in high-dimensional
settings remains a challenge. Recent work has advocated a two-step approach to improve …
settings remains a challenge. Recent work has advocated a two-step approach to improve …
[PDF][PDF] Locality adaptive discriminant analysis.
Abstract Linear Discriminant Analysis (LDA) is a popular technique for supervised
dimensionality reduction, and its performance is satisfying when dealing with Gaussian …
dimensionality reduction, and its performance is satisfying when dealing with Gaussian …
Estimation of wasserstein distances in the spiked transport model
J Niles-Weed, P Rigollet - Bernoulli, 2022 - projecteuclid.org
Estimation of Wasserstein distances in the Spiked Transport Model Page 1 Bernoulli 28(4),
2022, 2663–2688 https://doi.org/10.3150/21-BEJ1433 Estimation of Wasserstein distances …
2022, 2663–2688 https://doi.org/10.3150/21-BEJ1433 Estimation of Wasserstein distances …