We give the first representation-independent hardness results for PAC learning intersections of halfspaces, a central concept class in computational learning theory. Our hardness results are derived from two public-key cryptosystems due to Regev, which are based on the worst-case hardness of well-studied lattice problems. Specifically, we prove that a polynomial-time algorithm for PAC learning intersections of nε{lunate} halfspaces (for a constant ε{lunate} > 0) in n dimensions would yield a polynomial-time solution to over(O, ̃) (n1.5)-uSVP (unique shortest vector problem). We also prove that PAC learning intersections of nε{lunate} low-weight halfspaces would yield a polynomial-time quantum solution to over(O, ̃) (n1.5)-SVP and over(O, ̃) (n1.5)-SIVP (shortest vector problem and shortest independent vector problem, respectively). Our approach also yields the first representation-independent hardness results for learning polynomial-size depth-2 neural networks and polynomial-size depth-3 arithmetic circuits. © 2008 Elsevier Inc. All rights reserved.
CITATION STYLE
Klivans, A. R., & Sherstov, A. A. (2009). Cryptographic hardness for learning intersections of halfspaces. Journal of Computer and System Sciences, 75(1), 2–12. https://doi.org/10.1016/j.jcss.2008.07.008
Mendeley helps you to discover research relevant for your work.