We consider estimation models of the form Y X * + N, where X * is some m-dimensional structured signal we wish to recover, and N is symmetrically distributed noise that may be unbounded in all but a small α fraction of the entries. This setting captures problems such as (sparse) linear regression, (sparse) principal component analysis (PCA), and tensor PCA, even in the presence of oblivious outliers and heavy-tailed noise.We introduce a family of algorithms that under mild assumptions recover the signal X * in all estimation problems for which there exists a sum-of-squares algorithm that succeeds in recovering the signal X * when the noise N is Gaussian. This essentially shows that it is enough to design a sum-of-squares algorithm for an estimation problem with Gaussian additive noise in order to get the algorithm that works with the symmetric noise model.Our framework extends far beyond previous results on symmetric noise models and is even robust to an ε-fraction of adversarial perturbations. As concrete examples, we investigate two problems for which no efficient algorithms were known to work for heavy-tailed noise: tensor PCA and sparse PCA.For the former, our algorithm recovers the principal component in polynomial time when the signal-to-noise ratio is at least Õ(n p/4 /α), that matches (up to logarithmic factors) current best known algorithmic guarantees for Gaussian noise. For the latter, our algorithm runs in quasipolynomial time and matches the state-of-the-art guarantees for quasipolynomial time algorithms in the case of Gaussian noise. Using a reduction from the planted clique problem, we provide evidence that the quasipolynomial time is likely to be necessary for sparse PCA with symmetric noise.In our proofs we use bounds on the covering numbers of sets of pseudo-expectations, which we obtain by certifying in sum-of-squares upper bounds on the Gaussian complexities of sets of solutions. This approach for bounding the covering numbers of sets of pseudo-expectations may be interesting in its own right and may find other application in future works.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.