activity
20042022
most citedHigh-dimensional Ising model selection using -regularized logistic regression

538 citations · 1.8k across the 55 of their papers we have counts for

collaborators
Showing 2018Show all

11 papers · 1 filter

cs.LG2018

Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems

Dhruv Malik, Ashwin Pananjady, Kush Bhatia +3

We study derivative-free methods for policy optimization over the class of linear policies. We focus on characterizing the convergence rate of these methods when applied to linear-…

math.ST2018

Singularity, Misspecification, and the Convergence Rate of EM

Raaz Dwivedi, Nhat Ho, Koulik Khamaru +3

A line of recent work has analyzed the behavior of the Expectation-Maximization (EM) algorithm in the well-specified setting, in which the population likelihood is locally strongly…

cs.LG2018

L-Shapley and C-Shapley: Efficient Model Interpretation for Structured Data

Jianbo Chen, Le Song, Martin J. Wainwright +1

We study instancewise feature importance scoring as a method for model interpretation. Any such method yields, for each predicted instance, a vector of importance scores associated…

stat.ML2018

Towards Optimal Estimation of Bivariate Isotonic Matrices with Unknown Permutations

Cheng Mao, Ashwin Pananjady, Martin J. Wainwright

Many applications, including rank aggregation, crowd-labeling, and graphon estimation, can be modeled in terms of a bivariate isotonic matrix with unknown permutations acting on it…

stat.ML2018

Convergence guarantees for a class of non-convex and non-smooth optimization problems

Koulik Khamaru, Martin J. Wainwright

We consider the problem of finding critical points of functions that are non-convex and non-smooth. Studying a fairly broad class of such problems, we analyze the behavior of three…

math.ST2018

From Gauss to Kolmogorov: Localized Measures of Complexity for Ellipses

Yuting Wei, Billy Fang, Martin J. Wainwright

The Gaussian width is a fundamental quantity in probability, statistics and geometry, known to underlie the intrinsic difficulty of estimation and hypothesis testing. In this work,…