Estimating principal components under adversarial perturbations

Pranjal Awasthi, Xue Chen, Aravindan Vijayaraghavan

Research output: Contribution to journalArticlepeer-review

Abstract

Robustness is a key requirement for widespread deployment of machine learning algorithms, and has received much attention in both statistics and computer science. We study a natural model of robustness for high-dimensional statistical estimation problems that we call the adversarial perturbation model. An adversary can perturb every sample arbitrarily up to a specified magnitude δ measured in some ℓq norm, say ℓ. Our model is motivated by emerging paradigms such as low precision machine learning and adversarial training. We study the classical problem of estimating the top-r principal subspace of the Gaussian covariance matrix in high dimensions, under the adversarial perturbation model. We design a computationally efficient algorithm that given corrupted data, recovers an estimate of the top-r principal subspace with error that depends on a robustness parameter κ that we identify. This parameter corresponds to the q → 2 operator norm of the projector onto the principal subspace, and generalizes well-studied analytic notions of sparsity. Additionally, in the absence of corruptions, our algorithmic guarantees recover existing bounds for problems such as sparse PCA and its higher rank analogs. We also prove that the above dependence on the parameter κ is almost optimal asymptotically, not just in a minimax sense, but remarkably for every instance of the problem. This instance-optimal guarantee shows that the q → 2 operator norm of the subspace essentially characterizes the estimation error under adversarial perturbations.

Original languageEnglish (US)
JournalUnknown Journal
StatePublished - May 31 2020

ASJC Scopus subject areas

  • General

Fingerprint Dive into the research topics of 'Estimating principal components under adversarial perturbations'. Together they form a unique fingerprint.

Cite this