165 citations · 950 across the 71 of their papers we have counts for
4 papers · 2 filters
Settling the Robust Learnability of Mixtures of Gaussians
Allen Liu, Ankur Moitra
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 provabl…
Tensor Completion Made Practical
Allen Liu, Ankur Moitra
Tensor completion is a natural higher-order generalization of matrix completion where the goal is to recover a low-rank tensor from sparse observations of its entries. Existing alg…
Algorithmic Foundations for the Diffraction Limit
Sitan Chen, Ankur Moitra
For more than a century and a half it has been widely-believed (but was never rigorously shown) that the physics of diffraction imposes certain fundamental limits on the resolution…
Rigorous Guarantees for Tyler's M-estimator via quantum expansion
Cole Franks, Ankur Moitra
Estimating the shape of an elliptical distribution is a fundamental problem in statistics. One estimator for the shape matrix, Tyler's M-estimator, has been shown to have many appe…