Smoothed Agnostic Learning of Halfspaces over the Hypercube
By: Yiwen Kou, Raghu Meka
Potential Business Impact:
Learns patterns in computer code faster.
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.
Similar Papers
A Fully Polynomial-Time Algorithm for Robustly Learning Halfspaces over the Hypercube
Data Structures and Algorithms
Teaches computers to learn from messy, bad data.
Learning Intersections of Halfspaces under Factorizable Distribution
Machine Learning (CS)
Finds patterns faster than old methods.
Halfspaces are hard to test with relative error
Computational Complexity
Makes testing simple computer programs harder.