Statistical bounds for entropic optimal transport: sample complexity and the central limit theorem

G Mena, J Niles-Weed - Advances in neural information …, 2019‏ - proceedings.neurips.cc
We prove several fundamental statistical bounds for entropic OT with the squared Euclidean
cost between subgaussian probability measures in arbitrary dimension. First, through a new …

[PDF][PDF] Statistical optimal transport

S Chewi, J Niles-Weed, P Rigollet - arxiv preprint arxiv:2407.18163, 2024‏ - arxiv.org
Statistical Optimal Transport arxiv:2407.18163v2 [math.ST] 7 Nov 2024 Page 1 Statistical
Optimal Transport Sinho Chewi Yale Jonathan Niles-Weed NYU Philippe Rigollet MIT …

On the sample complexity of entropic optimal transport

P Rigollet, AJ Stromme - The Annals of Statistics, 2025‏ - projecteuclid.org
We study the sample complexity of entropic optimal transport in high dimensions using
computationally efficient plug-in estimators. We significantly advance the state of the art by …

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 …

An improved central limit theorem and fast convergence rates for entropic transportation costs

E del Barrio, AG Sanz, JM Loubes… - SIAM Journal on …, 2023‏ - SIAM
We prove a central limit theorem for the entropic transportation cost between subgaussian
probability measures, centered at the population cost. This is the first result which allows for …

Estimating the rate-distortion function by Wasserstein gradient descent

Y Yang, S Eckstein, M Nutz… - Advances in Neural …, 2024‏ - proceedings.neurips.cc
In the theory of lossy compression, the rate-distortion (RD) function $ R (D) $ describes how
much a data source can be compressed (in bit-rate) at any given level of fidelity (distortion) …

Minimax estimation of smooth optimal transport maps

JC Hütter, P Rigollet - 2021‏ - projecteuclid.org
The supplementary materials contain more background on convex functions, wavelets and
empirical processes, as well as tools to prove lower bounds, alternative assumptions based …

pop-cosmos: A comprehensive picture of the galaxy population from COSMOS data

J Alsing, S Thorp, S Deger, HV Peiris… - The Astrophysical …, 2024‏ - iopscience.iop.org
We present pop-cosmos: a comprehensive model characterizing the galaxy population,
calibrated to 140,938 (r< 25 selected) galaxies from the Cosmic Evolution Survey …

Massively scalable Sinkhorn distances via the Nyström method

J Altschuler, F Bach, A Rudi… - Advances in neural …, 2019‏ - proceedings.neurips.cc
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 …

Statistical analysis of Wasserstein distributionally robust estimators

J Blanchet, K Murthy… - Tutorials in Operations …, 2021‏ - pubsonline.informs.org
We consider statistical methods that invoke a min-max distributionally robust formulation to
extract good out-of-sample performance in data-driven optimization and learning problems …