Cryptographic hardness for learning intersections of halfspaces

Journal of Computer and System Sciences

Volumn 75, Issue 1, 2009, Pages 2-12

  Klivans, Adam R ^a   Sherstov, Alexander A ^a  

^a University of Texas at Austin   (United States)

Author keywords

Computational learning theory; Cryptographic hardness results; Intersections of halfspaces; Lattice based cryptography

Indexed keywords

COMPUTATION THEORY; GEOMETRY; LATTICE THEORY; POLYNOMIAL APPROXIMATION; PUBLIC KEY CRYPTOGRAPHY;

ARITHMETIC CIRCUIT; COMPUTATIONAL LEARNING THEORY; CRYPTOGRAPHIC HARDNESS RESULTS; INTERSECTIONS OF HALFSPACES; LATTICE-BASED CRYPTOGRAPHY; POLYNOMIAL-TIME ALGORITHMS; PUBLIC KEY CRYPTOSYSTEMS; SHORTEST VECTOR PROBLEM;

HARDNESS;

EID: 56249100680     PISSN: 00220000     EISSN: 10902724     Source Type: Journal    
DOI: 10.1016/j.jcss.2008.07.008     Document Type: Article

References (32)

1. Aharonov D., and Regev O. Lattice problems in NP ∩ coNP. J. ACM 52 5 (2005) 749-765
2. M. Ajtai, C. Dwork, A public-key cryptosystem with worst-case/average-case equivalence, in: Proceedings of the 29th Symposium on Theory of Computing (STOC), 1997
3. M. Alekhnovich, M. Braverman, V. Feldman, A. Klivans, T. Pitassi, Learnability and automatizability, in: Proceedings of the 45th Annual Symposium on Foundations of Computer Science (FOCS), 2004
4. Beimel A., Bergadano F., Bshouty N.H., Kushilevitz E., and Varricchio S. Learning functions represented as multiplicity automata. J. ACM 47 3 (2000) 506-530
5. Blum A.L., and Rivest R.L. Training a 3-node neural network is NP-complete. Neural Networks 5 (1992) 117-127
6. Blum L., Blum M., and Shub M. A simple unpredictable pseudo-random number generator. SIAM J. Comput. 15 2 (1986) 364-383
7. V. Feldman, P. Gopalan, S. Khot, A.K. Ponnuswami, New results for learning noisy parities and halfspaces, in: Proceedings of the 47th Annual Symposium on Foundations of Computer Science (FOCS), 2006
8. Furst M.L., Saxe J.B., and Sipser M. Parity, circuits, and the polynomial-time hierarchy. Math. Systems Theory 17 1 (1984) 13-27
9. Goldmann M., Håstad J., and Razborov A.A. Majority gates vs. general weighted threshold gates. Comput. Complexity 2 (1992) 277-300
10. Goldmann M., and Karpinski M. Simulating threshold circuits by majority circuits. SIAM J. Comput. 27 1 (1998) 230-246
11. Håstad J. Computational Limitations of Small-Depth Circuits (1987), MIT Press, Cambridge, MA, USA
12. Kearns M., and Valiant L. Cryptographic limitations on learning Boolean formulae and finite automata. J. ACM 41 1 (1994) 67-95
13. Kearns M.J., and Vazirani U.V. An Introduction to Computational Learning Theory (1994), MIT Press, Cambridge, MA, USA
14. M. Kharitonov, Cryptographic hardness of distribution-specific learning, in: Proceedings of the 25th Symposium on Theory of Computing (STOC), 1993
15. Kharitonov M. Cryptographic lower bounds for learnability of Boolean functions on the uniform distribution. J. Comput. System Sci. 50 3 (1995) 600-610
16. A. Klivans, A. Shpilka, Learning arithmetic circuits via partial derivatives, in: Proceedings of the Workshop on Computational Learning Theory (COLT), 2003
17. Klivans A.R., O'Donnell R., and Servedio R.A. Learning intersections and thresholds of halfspaces. J. Comput. System Sci. 68 4 (2004) 808-840
18. Klivans A.R., and Servedio R.A. Learning intersections of halfspaces with a margin. J. Comput. System Sci. 74 1 (2008) 35-48
19. Klivans A.R., and Sherstov A.A. Unconditional lower bounds for learning intersections of halfspaces. Machine Learning 69 2-3 (2007) 97-114
20. A.R. Klivans, D.A. Spielman, Randomness efficient identity testing of multivariate polynomials, in: Proceedings of the 33rd Symposium on Theory of Computing (STOC), 2001
21. Kwek S., and Pitt L. PAC learning intersections of halfspaces with membership queries. Algorithmica 22 1/2 (1998) 53-75
22. Mansour Y. Randomized interpolation and approximation of sparse polynomials. SIAM J. Comput. 24 2 (1995) 357-368
23. Regev O. New lattice based cryptographic constructions. in: Proceedings of the 35th Symposium on Theory of Computing (STOC), 2003, final version in. J. ACM 51 6 (2004) 899-942
24. O. Regev, On lattices, learning with errors, random linear codes, and cryptography, in: Proceedings of the 37th Symposium on Theory of Computing (STOC), 2005
25. O. Regev, personal communication, 2006
26. O. Regev, Lattice-based cryptography, in: Proceedings of the 26th Annual International Cryptology Conference (CRYPTO), vol. 4117, 2006
27. Regev O. On the complexity of lattice problems with polynomial approximation factors, survey prepared for the LLL+25 conference. available at (June 2007). http://www.cs.tau.ac.il/~odedr
28. Schapire R.E., and Sellie L. Learning sparse multivariate polynomials over a field with queries and counterexamples. J. Comput. System Sci. 52 2 (1996) 201-213
29. Siu K.-Y., and Roychowdhury V.P. On optimal depth threshold circuits for multiplication and related problems. SIAM J. Discrete Math. 7 2 (1994) 284-292
30. Valiant L.G. A theory of the learnable. Comm. ACM 27 11 (1984) 1134-1142
31. S. Vempala, A random sampling based algorithm for learning the intersection of halfspaces, in: Proceedings of the 38th Annual Symposium on Foundations of Computer Science, 1997
32. Wegener I. Optimal lower bounds on the depth of polynomial-size threshold circuits for some arithmetic functions. Inform. Process. Lett. 46 2 (1993) 85-87