49 citations · 234 across the 21 of their papers we have counts for
5 papers · 1 filter
Statistical Query Algorithms and Low-Degree Tests Are Almost Equivalent
Matthew Brennan, Guy Bresler, Samuel B. Hopkins +2
Researchers currently use a number of approaches to predict and substantiate information-computation gaps in high-dimensional statistical estimation problems. A prominent approach…
Estimating Rank-One Spikes from Heavy-Tailed Noise via Self-Avoiding Walks
Jingqiu Ding, Samuel B. Hopkins, David Steurer
We study symmetric spiked matrix models with respect to a general class of noise distributions. Given a rank-1 deformation of a random noise matrix, whose entries are independently…
Smoothed Complexity of 2-player Nash Equilibria
Shant Boodaghians, Joshua Brakensiek, Samuel B. Hopkins +1
We prove that computing a Nash equilibrium of a two-player () game with payoffs in is PPAD-hard (under randomized reductions) even in the smoothed analysis set…
Robust and Heavy-Tailed Mean Estimation Made Simple, via Regret Minimization
Samuel B. Hopkins, Jerry Li, Fred Zhang
We study the problem of estimating the mean of a distribution in high dimensions when either the samples are adversarially corrupted or the distribution is heavy-tailed. Recent dev…
Robustly Learning any Clusterable Mixture of Gaussians
Ilias Diakonikolas, Samuel B. Hopkins, Daniel Kane +1
We study the efficient learnability of high-dimensional Gaussian mixtures in the outlier-robust setting, where a small constant fraction of the data is adversarially corrupted. We…