Recent advances in algorithmic high-dimensional robust statistics
I Diakonikolas, DM Kane - arXiv preprint arXiv:1911.05911, 2019 - arxiv.org
Learning in the presence of outliers is a fundamental problem in statistics. Until recently, all
known efficient unsupervised learning algorithms were very sensitive to outliers in high …
known efficient unsupervised learning algorithms were very sensitive to outliers in high …
Robust estimators in high-dimensions without the computational intractability
We study high-dimensional distribution learning in an agnostic setting where an adversary is
allowed to arbitrarily corrupt an ε-fraction of the samples. Such questions have a rich history …
allowed to arbitrarily corrupt an ε-fraction of the samples. Such questions have a rich history …
Mixture models, robustness, and sum of squares proofs
SB Hopkins, J Li - Proceedings of the 50th Annual ACM SIGACT …, 2018 - dl.acm.org
We use the Sum of Squares method to develop new efficient algorithms for learning well-
separated mixtures of Gaussians and robust mean estimation, both in high dimensions, that …
separated mixtures of Gaussians and robust mean estimation, both in high dimensions, that …
Estimation contracts for outlier-robust geometric perception
L Carlone - Foundations and Trends® in Robotics, 2023 - nowpublishers.com
Outlier-robust estimation is a fundamental problem and has been extensively investigated
by statisticians and practitioners. The last few years have seen a convergence across …
by statisticians and practitioners. The last few years have seen a convergence across …
Robust inference via generative classifiers for handling noisy labels
Large-scale datasets may contain significant proportions of noisy (incorrect) class labels,
and it is well-known that modern deep neural networks (DNNs) poorly generalize from such …
and it is well-known that modern deep neural networks (DNNs) poorly generalize from such …
Robust moment estimation and improved clustering via sum of squares
We develop efficient algorithms for estimating low-degree moments of unknown distributions
in the presence of adversarial outliers and design a new family of convex relaxations for k …
in the presence of adversarial outliers and design a new family of convex relaxations for k …
List-decodable robust mean estimation and learning mixtures of spherical gaussians
We study the problem of list-decodable (robust) Gaussian mean estimation and the related
problem of learning mixtures of separated spherical Gaussians. In the former problem, we …
problem of learning mixtures of separated spherical Gaussians. In the former problem, we …
Robustly learning a gaussian: Getting optimal error, efficiently
We study the fundamental problem of learning the parameters of a high-dimensional
Gaussian in the presence of noise—where an ε-fraction of our samples were chosen by an …
Gaussian in the presence of noise—where an ε-fraction of our samples were chosen by an …
Distribution-independent pac learning of halfspaces with massart noise
I Diakonikolas, T Gouleakis… - Advances in Neural …, 2019 - proceedings.neurips.cc
We study the problem of {\em distribution-independent} PAC learning of halfspaces in the
presence of Massart noise. Specifically, we are given a set of labeled examples $(\bx, y) …
presence of Massart noise. Specifically, we are given a set of labeled examples $(\bx, y) …
Mean estimation with sub-Gaussian rates in polynomial time
SB Hopkins - The Annals of Statistics, 2020 - JSTOR
We study polynomial time algorithms for estimating the mean of a heavytailed multivariate
random vector. We assume only that the random vector X has finite mean and covariance. In …
random vector. We assume only that the random vector X has finite mean and covariance. In …