261 citations · 347 across the 12 of their papers we have counts for
13 papers
Trajectory Inference with Smooth Schrödinger Bridges
Wanli Hong, Yuliang Shi, Jonathan Niles-Weed
Motivated by applications in trajectory inference and particle tracking, we introduce Smooth Schrödinger Bridges. Our proposal generalizes prior work by allowing the reference proc…
The Adversarial Consistency of Surrogate Risks for Binary Classification
Natalie Frank, Jonathan Niles-Weed
We study the consistency of surrogate risks for robust binary classification. It is common to learn robust classifiers by adversarial training, which seeks to minimize the expected…
Sharp thresholds in inference of planted subgraphs
Elchanan Mossel, Jonathan Niles-Weed, Youngtak Sohn +2
A major question in the study of the Erdős--Rényi random graph is to understand the probability that it contains a given subgraph. This study originated in classical work of Erdős…
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…
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 .…
The Consistency of Adversarial Training for Binary Classification
Natalie S. Frank, Jonathan Niles-Weed
Robustness to adversarial perturbations is of paramount concern in modern machine learning. One of the state-of-the-art methods for training robust classifiers is adversarial train…
Existence and Minimax Theorems for Adversarial Surrogate Risks in Binary Classification
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. We pr…
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…
It was "all" for "nothing": sharp phase transitions for noiseless discrete channels
Jonathan Niles-Weed, Ilias Zadik
We establish a phase transition known as the "all-or-nothing" phenomenon for noiseless discrete channels. This class of models includes the Bernoulli group testing model and the pl…
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…
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…
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…
Estimation under group actions: recovering orbits from invariants
Afonso S. Bandeira, Ben Blum-Smith, Joe Kileel +3
We study a class of orbit recovery problems in which we observe independent copies of an unknown element of , each linearly acted upon by a random element of some gro…