Sample-Optimal PAC Learning of Halfspaces with Malicious Noise

Abstract

We study efficient PAC learning of homogeneous halfspaces in ${\mathbb{R}}^d$ in the presence of malicious noise of Valiant (1985). This is a challenging noise model and only until recently has near-optimal noise tolerance bound been established under the mild condition that the unlabeled data distribution is isotropic log-concave. However, it remains unsettled how to obtain the optimal sample complexity simultaneously. In this work, we present a new analysis for the algorithm of Awasthi et al. (2017) and show that it essentially achieves the near-optimal sample complexity bound of $\tilde{O}(d)$, improving the best known result of $\tilde{O}(d^2)$. Our main ingredient is a novel incorporation of a matrix Chernoff-type inequality to bound the spectrum of an empirical covariance matrix for well-behaved distributions, in conjunction with a careful exploration of the localization schemes of Awasthi et al. (2017). We further extend the algorithm and analysis to the more general and stronger nasty noise model of Bshouty et al. (2002), showing that it is still possible to achieve near-optimal noise tolerance and sample complexity in polynomial time.

arXiv commentAccepted to ICML 2021. V2 and V3 polished writing

References in corpus (6)

• Risk bounds for statistical learning
• Recent Advances in Algorithmic High-Dimensional Robust Statistics
• Distribution-Independent PAC Learning of Halfspaces with Massart Noise
• Efficient active learning of sparse halfspaces with arbitrary bounded noise
• A Polynomial Time Algorithm for Learning Halfspaces with Tsybakov Noise
• On the Power of Localized Perceptron for Label-Optimal Learning of Halfspaces with Adversarial Noise