43 citations · 90 across the 13 of their papers we have counts for
13 papers
State evolution beyond first-order methods I: Rigorous predictions and finite-sample guarantees
Michael Celentano, Chen Cheng, Ashwin Pananjady +1
We develop a toolbox for exact analysis of iterative algorithms on a class of high-dimensional nonconvex optimization problems with random data. While prior work has shown that low…
Mean-field variational inference with the TAP free energy: Geometric and statistical properties in linear models
Michael Celentano, Zhou Fan, Licong Lin +1
We study mean-field variational inference in a Bayesian linear model when the sample size n is comparable to the dimension p. In high dimensions, the common approach of minimizing…
Challenges of the inconsistency regime: Novel debiasing methods for missing data models
Michael Celentano, Martin J. Wainwright
We study semi-parametric estimation of the population mean when data is observed missing at random (MAR) in the "inconsistency regime", in which neither the outcome model n…
Integral Probability Metrics Meet Neural Networks: The Radon-Kolmogorov-Smirnov Test
Seunghoon Paik, Michael Celentano, Alden Green +1
Integral probability metrics (IPMs) constitute a general class of nonparametric two-sample tests that are based on maximizing the mean difference between samples from one distribut…
Sudakov-Fernique post-AMP, and a new proof of the local convexity of the TAP free energy
Michael Celentano
In many problems in modern statistics and machine learning, it is often of interest to establish that a first order method on a non-convex risk function eventually enters a region…
The high-dimensional asymptotics of first order methods with random data
Michael Celentano, Chen Cheng, Andrea Montanari
We study a class of deterministic flows in , parametrized by a random matrix with i.i.d. centered subgaussian…