Computational optimal transport: With applications to data science

G Peyré, M Cuturi - Foundations and Trends® in Machine …, 2019‏ - nowpublishers.com
Optimal transport (OT) theory can be informally described using the words of the French
mathematician Gaspard Monge (1746–1818): A worker with a shovel in hand has to move a …

Kernel mean embedding of distributions: A review and beyond

K Muandet, K Fukumizu… - … and Trends® in …, 2017‏ - nowpublishers.com
A Hilbert space embedding of a distribution—in short, a kernel mean embedding—has
recently emerged as a powerful tool for machine learning and statistical inference. The basic …

Learning generative models with sinkhorn divergences

A Genevay, G Peyré, M Cuturi - International Conference on …, 2018‏ - proceedings.mlr.press
The ability to compare two degenerate probability distributions, that is two distributions
supported on low-dimensional manifolds in much higher-dimensional spaces, is a crucial …

Estimating individual treatment effect: generalization bounds and algorithms

U Shalit, FD Johansson… - … conference on machine …, 2017‏ - proceedings.mlr.press
There is intense interest in applying machine learning to problems of causal inference in
fields such as healthcare, economics and education. In particular, individual-level causal …

Sample complexity of Sinkhorn divergences

A Genevay, L Chizat, F Bach… - The 22nd …, 2019‏ - proceedings.mlr.press
Optimal transport (OT) and maximum mean discrepancies (MMD) are now routinely used in
machine learning to compare probability measures. We focus in this paper on Sinkhorn …

Stochastic optimization for large-scale optimal transport

A Genevay, M Cuturi, G Peyré… - Advances in neural …, 2016‏ - proceedings.neurips.cc
Optimal transport (OT) defines a powerful framework to compare probability distributions in a
geometrically faithful way. However, the practical impact of OT is still limited because of its …

Frameworks and results in distributionally robust optimization

H Rahimian, S Mehrotra - Open Journal of Mathematical Optimization, 2022‏ - numdam.org
The concepts of risk aversion, chance-constrained optimization, and robust optimization
have developed significantly over the last decade. The statistical learning community has …

A unified recipe for deriving (time-uniform) PAC-Bayes bounds

B Chugg, H Wang, A Ramdas - Journal of Machine Learning Research, 2023‏ - jmlr.org
We present a unified framework for deriving PAC-Bayesian generalization bounds. Unlike
most previous literature on this topic, our bounds are anytime-valid (ie, time-uniform) …

Equivalence of distance-based and RKHS-based statistics in hypothesis testing

D Sejdinovic, B Sriperumbudur, A Gretton… - The annals of …, 2013‏ - JSTOR
We provide a unifying framework linking two classes of statistics used in two-sample and
independence testing: on the one hand, the energy distances and distance covariances …

[كتاب][B] Basics and trends in sensitivity analysis: Theory and practice in R

S Da Veiga, F Gamboa, B Iooss, C Prieur - 2021‏ - SIAM
In many fields, such as environmental risk assessment, agronomic system behavior,
aerospace engineering, and nuclear safety, mathematical models turned into computer code …