Smoothed Agnostic Learning of Halfspaces over the Hypercube

TL;DR

This paper introduces a new smoothed analysis framework for learning Boolean halfspaces over the hypercube using random bit flips, providing the first efficient algorithm with theoretical guarantees in this discrete setting.

Contribution

It develops a discrete smoothed analysis model for agnostic learning of halfspaces and offers the first efficient algorithm with provable guarantees under this model.

Findings

Efficient algorithm for smoothed agnostic learning of halfspaces over the hypercube.

Runtime and sample complexity depend on input distribution parameters.

Bridges the gap between worst-case hardness and practical learnability in discrete domains.

Abstract

Agnostic learning of Boolean halfspaces is a fundamental problem in computational learning theory, but it is known to be computationally hard even for weak learning. Recent work [CKKMK24] proposed smoothed analysis as a way to bypass such hardness, but existing frameworks rely on additive Gaussian perturbations, making them unsuitable for discrete domains. We introduce a new smoothed agnostic learning framework for Boolean inputs, where perturbations are modeled via random bit flips. This defines a natural discrete analogue of smoothed optimality generalizing the Gaussian case. Under strictly subexponential assumptions on the input distribution, we give an efficient algorithm for learning halfspaces in this model, with runtime and sample complexity approximately n raised to a poly(1/(sigma * epsilon)) factor. Previously, such algorithms were known only with strong structural assumptions for the discrete hypercube, for example, independent coordinates or symmetric distributions. Our result provides the first computationally efficient guarantee for smoothed agnostic learning of halfspaces over the Boolean hypercube, bridging the gap between worst-case intractability and practical learnability in discrete settings.