activity
20202022
most citedSinkhorn EM: An Expectation-Maximization algorithm based on entropic optimal transport

7 citations · 14 across the 4 of their papers we have counts for

collaborators

6 papers

math.CO20221 cited

A second moment proof of the spread lemma

Elchanan Mossel, Jonathan Niles-Weed, Nike Sun +1

This note concerns a well-known result which we term the ``spread lemma,'' which establishes the existence (with high probability) of a desired structure in a random set. The sprea…

math.CO2022

On the Second Kahn--Kalai Conjecture

Elchanan Mossel, Jonathan Niles-Weed, Nike Sun +1

For any given graph , we are interested in , the minimal such that the Erdős-Rényi graph contains a copy of with probability at least .…

cs.DS2021

Strong recovery of geometric planted matchings

Dmitriy Kunisky, Jonathan Niles-Weed

We study the problem of efficiently recovering the matching between an unlabelled collection of points in and a small random perturbation of those points. We con…

math.ST20206 cited

The All-or-Nothing Phenomenon in Sparse Tensor PCA

Jonathan Niles-Weed, Ilias Zadik

We study the statistical problem of estimating a rank-one sparse tensor corrupted by additive Gaussian noise, a model also known as sparse tensor PCA. We show that for Bernoulli an…

cs.LG2020

Early-Learning Regularization Prevents Memorization of Noisy Labels

Sheng Liu, Jonathan Niles-Weed, Narges Razavian +1

We propose a novel framework to perform classification via deep learning in the presence of noisy annotations. When trained on noisy labels, deep neural networks have been observed…

stat.ML20207 cited

Sinkhorn EM: An Expectation-Maximization algorithm based on entropic optimal transport

Gonzalo Mena, Amin Nejatbakhsh, Erdem Varol +1

We study Sinkhorn EM (sEM), a variant of the expectation maximization (EM) algorithm for mixtures based on entropic optimal transport. sEM differs from the classic EM algorithm in…