Polynomial time and private learning of unbounded gaussian mixture models

J Arbas, H Ashtiani, C Liaw - International Conference on …, 2023 - proceedings.mlr.press
We study the problem of privately estimating the parameters of $ d $-dimensional Gaussian
Mixture Models (GMMs) with $ k $ components. For this, we develop a technique to reduce …

Settling the robust learnability of mixtures of gaussians

A Liu, A Moitra - Proceedings of the 53rd Annual ACM SIGACT …, 2021 - dl.acm.org
This work represents a natural coalescence of two important lines of work–learning mixtures
of Gaussians and algorithmic robust statistics. In particular we give the first provably robust …

Minimax rates for robust community detection

A Liu, A Moitra - 2022 IEEE 63rd Annual Symposium on …, 2022 - ieeexplore.ieee.org
In this work, we study the problem of community detection in the stochastic block model with
adversarial node corruptions. Our main result is an efficient algorithm that can tolerate an ϵ …

Distribution learnability and robustness

S Ben-David, A Bie, G Kamath… - Advances in Neural …, 2024 - proceedings.neurips.cc
We examine the relationship between learnability and robust learnability for the problem of
distribution learning. We show that learnability implies robust learnability if the adversary …

Tensor decompositions meet control theory: learning general mixtures of linear dynamical systems

A Bakshi, A Liu, A Moitra, M Yau - … Conference on Machine …, 2023 - proceedings.mlr.press
Abstract Recently Chen and Poor initiated the study of learning mixtures of linear dynamical
systems. While linear dynamical systems already have wide-ranging applications in …

Robustly learning general mixtures of gaussians

A Liu, A Moitra - Journal of the ACM, 2023 - dl.acm.org
This work represents a natural coalescence of two important lines of work—learning
mixtures of Gaussians and algorithmic robust statistics. In particular, we give the first …

Mixtures of gaussians are privately learnable with a polynomial number of samples

M Afzali, H Ashtiani, C Liaw - ar**: unmasking failure modes
JY Huang, DR Burt, TD Nguyen, Y Shen… - ar** a very small fraction of data
points from a study could change its substantive conclusions. Finding the worst-case data …

Robust voting rules from algorithmic robust statistics

A Liu, A Moitra - Proceedings of the 2023 Annual ACM-SIAM …, 2023 - SIAM
Maximum likelihood estimation furnishes powerful insights into voting theory, and the design
of voting rules. However the MLE can usually be badly corrupted by a single outlying …