activity
20162023
most citedImproved Discretization Analysis for Underdamped Langevin Monte Carlo

5 citations · 6 across the 5 of their papers we have counts for

collaborators

5 papers

stat.ML2023

Gradient-Based Feature Learning under Structured Data

Alireza Mousavi-Hosseini, Denny Wu, Taiji Suzuki +1

Recent works have demonstrated that the sample complexity of gradient-based learning of single index models, i.e. functions that depend on a 1-dimensional projection of the input d…

math.ST2023

Mean-Square Analysis of Discretized Itô Diffusions for Heavy-tailed Sampling

Ye He, Tyler Farghly, Krishnakumar Balasubramanian +1

We analyze the complexity of sampling from a class of heavy-tailed distributions by discretizing a natural class of Itô diffusions associated with weighted Poincaré inequalities. B…

math.ST20235 cited

Improved Discretization Analysis for Underdamped Langevin Monte Carlo

Matthew Zhang, Sinho Chewi, Mufan Bill Li +2

Underdamped Langevin Monte Carlo (ULMC) is an algorithm used to sample from unnormalized densities by leveraging the momentum of a particle moving in a potential well. We provide a…

cs.LG2022

-DkNN: Out-of-Distribution Detection Through Statistical Testing of Deep Representations

Adam Dziedzic, Stephan Rabanser, Mohammad Yaghini +3

The lack of well-calibrated confidence estimates makes neural networks inadequate in safety-critical domains such as autonomous driving or healthcare. In these settings, having the…

stat.ML20161 cited

Scalable Approximations for Generalized Linear Problems

Murat A. Erdogdu, Mohsen Bayati, Lee H. Dicker

In stochastic optimization, the population risk is generally approximated by the empirical risk. However, in the large-scale setting, minimization of the empirical risk may be comp…