24 citations · 92 across the 17 of their papers we have counts for
4 papers · 1 filter
Higher degree sum-of-squares relaxations robust against oblivious outliers
Tommaso d'Orsi, Rajai Nasser, Gleb Novikov +1
We consider estimation models of the form , where is some -dimensional signal we wish to recover, and is symmetrically distributed noise that may be unbounded…
Optimal SQ Lower Bounds for Learning Halfspaces with Massart Noise
Rajai Nasser, Stefan Tiegel
We give tight statistical query (SQ) lower bounds for learnining halfspaces in the presence of Massart noise. In particular, suppose that all labels are corrupted with probability…
Robust recovery for stochastic block models
Jingqiu Ding, Tommaso d'Orsi, Rajai Nasser +1
We develop an efficient algorithm for weak recovery in a robust version of the stochastic block model. The algorithm matches the statistical guarantees of the best known algorithms…
Consistent Estimation for PCA and Sparse Regression with Oblivious Outliers
Tommaso d'Orsi, Chih-Hung Liu, Rajai Nasser +3
We develop machinery to design efficiently computable and consistent estimators, achieving estimation error approaching zero as the number of observations grows, when facing an obl…