Jonathan Niles‐Weed

Statistics

Publications

Citations

662

H-Index

Active since

2018

Affiliations

Courant Institute of Mathematical Sciences(Current)

New York University

Massachusetts Institute of Technology

University of Applied Sciences and Arts of Southern Switzerland

Shandong University of Political Science and Law

Jonathan Niles‐Weed is an author at Courant Institute of Mathematical Sciences specializing in engineering, wasserstein distance, and probability theory.

Top concepts

EngineeringProbabilityWasserstein DistanceStatisticsEstimation TheoryApproximation TheoryStatistical InferenceData ScienceMathematical ProgrammingPre-training

Publications per year

2018–2024

Publications

Early-Learning Regularization Prevents Memorization of Noisy Labels

Sheng Liu, Jonathan Niles‐Weed, Narges Razavian et al. · arXiv (Cornell University) · 2020 · 261 citations · Full text

Natural Language Processing, Few-shot Learning, Novel Framework +14

Estimation of Wasserstein distances in the Spiked Transport Model

Jonathan Niles‐Weed, Philippe Rigollet · Bernoulli · 2022 · 68 citations

Density Estimation, Engineering, High-dimensional Method +14

Estimation under group actions: Recovering orbits from invariants

Afonso S. Bandeira, Ben Blum-Smith, Joe Kileel et al. · Applied and Computational Harmonic Analysis · 2023 · 58 citations · Full text

State Estimation, Lie Group, Engineering +4

Early-Learning Regularization Prevents Memorization of Noisy Labels

Sheng Liu, Jonathan Niles‐Weed, Narges Razavian et al. · Neural Information Processing Systems · 2020 · 58 citations

Few-shot Learning, Structured Prediction, Engineering +16

Minimax estimation of smooth densities in Wasserstein distance

Jonathan Niles‐Weed, Quentin Berthet · The Annals of Statistics · 2022 · 30 citations

Density Estimation, Engineering, Semi-nonparametric Estimation +13

1–5 of 14