2 code implementations • NeurIPS 2020 • Sheng Liu, Jonathan Niles-Weed, Narges Razavian, Carlos Fernandez-Granda
In contrast with existing approaches, which use the model output during early learning to detect the examples with clean labels, and either ignore or attempt to correct the false labels, we take a different route and instead capitalize on early learning via regularization.
Ranked #4 on Learning with noisy labels on CIFAR-10N-Random2
1 code implementation • 26 Jul 2021 • Tudor Manole, Sivaraman Balakrishnan, Jonathan Niles-Weed, Larry Wasserman
Our work also provides new bounds on the risk of corresponding plugin estimators for the quadratic Wasserstein distance, and we show how this problem relates to that of estimating optimal transport maps using stability arguments for smooth and strongly convex Brenier potentials.
no code implementations • NeurIPS 2019 • Jason Altschuler, Francis Bach, Alessandro Rudi, Jonathan Niles-Weed
The Sinkhorn "distance", a variant of the Wasserstein distance with entropic regularization, is an increasingly popular tool in machine learning and statistical inference.
no code implementations • 8 Feb 2020 • Marco Cuturi, Olivier Teboul, Jonathan Niles-Weed, Jean-Philippe Vert
Low rank matrix factorization is a fundamental building block in machine learning, used for instance to summarize gene expression profile data or word-document counts.
no code implementations • 30 Jun 2020 • Gonzalo Mena, Amin Nejatbakhsh, Erdem Varol, Jonathan Niles-Weed
We study Sinkhorn EM (sEM), a variant of the expectation maximization (EM) algorithm for mixtures based on entropic optimal transport.
no code implementations • ICML 2020 • Marco Cuturi, Olivier Teboul, Jonathan Niles-Weed, Jean-Philippe Vert
Low rank matrix factorization is a fundamental building block in machine learning, used for instance to summarize gene expression profile data or word-document counts.
no code implementations • 11 Jan 2021 • Dylan J. Altschuler, Jonathan Niles-Weed
A recent approach to the Beck-Fiala conjecture, a fundamental problem in combinatorics, has been to understand when random integer matrices have constant discrepancy.
Probability Discrete Mathematics Combinatorics
no code implementations • 6 Feb 2021 • De Huang, Jonathan Niles-Weed, Rachel Ward
We analyze Oja's algorithm for streaming $k$-PCA and prove that it achieves performance nearly matching that of an optimal offline algorithm.
no code implementations • 24 Feb 2021 • Jonathan Niles-Weed, Ilias Zadik
We establish a phase transition known as the "all-or-nothing" phenomenon for noiseless discrete channels.
Statistics Theory Information Theory Information Theory Probability Statistics Theory
no code implementations • 24 Sep 2021 • Aram-Alexandre Pooladian, Jonathan Niles-Weed
We develop a computationally tractable method for estimating the optimal map between two distributions over $\mathbb{R}^d$ with rigorous finite-sample guarantees.
no code implementations • 21 Nov 2021 • Sheng Liu, Aakash Kaku, Weicheng Zhu, Matan Leibovich, Sreyas Mohan, Boyang Yu, Haoxiang Huang, Laure Zanna, Narges Razavian, Jonathan Niles-Weed, Carlos Fernandez-Granda
Reliable probability estimation is of crucial importance in many real-world applications where there is inherent (aleatoric) uncertainty.
no code implementations • 19 Apr 2022 • Eustasio del Barrio, Alberto Gonzalez-Sanz, Jean-Michel Loubes, Jonathan Niles-Weed
We prove a central limit theorem for the entropic transportation cost between subgaussian probability measures, centered at the population cost.
no code implementations • 18 Jun 2022 • Natalie S. Frank, Jonathan Niles-Weed
Robustness to adversarial perturbations is of paramount concern in modern machine learning.
no code implementations • 18 Jun 2022 • Natalie S. Frank, Jonathan Niles-Weed
Adversarial training is one of the most popular methods for training methods robust to adversarial attacks, however, it is not well-understood from a theoretical perspective.
no code implementations • 26 Jun 2022 • Xin Bing, Florentina Bunea, Jonathan Niles-Weed
Our results establish this metric to be a canonical choice.
no code implementations • 29 Oct 2022 • Tom Tirer, Haoxiang Huang, Jonathan Niles-Weed
In this paper, we propose a richer model that can capture this phenomenon by forcing the features to stay in the vicinity of a predefined features matrix (e. g., intermediate features).
no code implementations • 7 Dec 2022 • Vincent Divol, Jonathan Niles-Weed, Aram-Alexandre Pooladian
To ensure identifiability, we assume that $T = \nabla \varphi_0$ is the gradient of a convex function, in which case $T$ is known as an \emph{optimal transport map}.
no code implementations • 26 Jan 2023 • Aram-Alexandre Pooladian, Vincent Divol, Jonathan Niles-Weed
We consider the problem of estimating the optimal transport map between two probability distributions, $P$ and $Q$ in $\mathbb R^d$, on the basis of i. i. d.
no code implementations • NeurIPS 2023 • Natalie Frank, Jonathan Niles-Weed
We study the consistency of surrogate risks for robust binary classification.
no code implementations • 20 Jun 2023 • Michal Klein, Aram-Alexandre Pooladian, Pierre Ablin, Eugène Ndiaye, Jonathan Niles-Weed, Marco Cuturi
Because of such difficulties, existing approaches rarely depart from the default choice of estimating such maps with the simple squared-Euclidean distance as the ground cost, $c(x, y)=\|x-y\|^2_2$.