Search Results for author:
Found 4 papers, 1 papers with code
A general theory for robust clustering via trimmed mean
In this paper, we introduce a hybrid clustering technique with a novel multivariate trimmed mean type centroid estimate to produce mislabeling guarantees under a weak initialization condition for general error distributions around the centroids.
Adversarially robust clustering with optimality guarantees
In the absence of outliers, in fixed dimensions, our theoretical guarantees are similar to that of the Lloyd algorithm.
Support Recovery with Stochastic Gates: Theory and Application for Linear Models
Consider the problem of simultaneous estimation and support recovery of the coefficient vector in a linear data model with additive Gaussian noise.
Extrapolating the profile of a finite population
Nevertheless, we show that in the sublinear regime of $m =\omega(k/\log k)$, it is possible to consistently estimate in total variation the \emph{profile} of the population, defined as the empirical distribution of the sizes of each type, which determines many symmetric properties of the population.
