Weights of Exact Threshold Functions

  • László Babai
  • Kristoffer Arnsfelt Hansen
  • Vladimir V. Podolskii
  • Xiaoming Sun
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6281)

Abstract

We consider Boolean exact threshold functions defined by linear equations, and in general degree d polynomials. We give upper and lower bounds on the maximum magnitude (absolute value) of the coefficients required to represent such functions. These bounds are very close and in the linear case in particular they are almost matching. The quantity is the same as the maximum magnitude of integer coefficients of linear equations required to express every possible intersection of a hyperplane in R n and the Boolean cube {0,1} n , or in the general case intersections of hypersurfaces of degree d in R n and the Boolean cube {0,1} n . In the process we construct new families of ill-conditioned matrices. We further stratify the problem (in the linear case) in terms of the dimension k of the affine subspace spanned by the solutions, and give upper and lower bounds in this case as well. Our bounds here in terms of k leave a substantial gap, a challenge for future work.

Keywords

Boolean Function Linear Case Threshold Function Integer Weight Symmetric Boolean Function 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This is a preview of subscription content, log in to check access.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Agrawal, M., Arvind, V.: Geometric sets of low information content. Theoretical Computer Science 158(1-2), 193–219 (1996)MATHCrossRefMathSciNetGoogle Scholar
  2. 2.
    Alon, N., Vũ, V.H.: Anti-hadamard matrices, coin weighing, threshold gates, and indecomposable hypergraphs. Journal of Combinatorial Theory, Series A 79(1), 133–160 (1997)MATHCrossRefMathSciNetGoogle Scholar
  3. 3.
    Beigel, R.: Perceptrons, PP, and the polynomial hierarchy. Computational Complexity 4(4), 339–349 (1994)MATHCrossRefMathSciNetGoogle Scholar
  4. 4.
    Beigel, R., Tarui, J., Toda, S.: On probabilistic ACC circuits with an exact-threshold output gate. In: Ibaraki, T., Iwama, K., Yamashita, M., Inagaki, Y., Nishizeki, T. (eds.) ISAAC 1992. LNCS, vol. 650, pp. 420–429. Springer, Heidelberg (1992)Google Scholar
  5. 5.
    Faddeev, D.K., Sominskii, I.S.: Problems in Higher Algebra. W.H. Freeman, New York (1965)Google Scholar
  6. 6.
    Green, F.: A complex-number fourier technique for lower bounds on the mod-m degree. Computational Complexity 9(1), 16–38 (2000)MATHCrossRefMathSciNetGoogle Scholar
  7. 7.
    Hansen, K.A.: Computing symmetric boolean functions by circuits with few exact threshold gates. In: Lin, G. (ed.) COCOON 2007. LNCS, vol. 4598, pp. 448–458. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  8. 8.
    Hansen, K.A.: Depth reduction for circuits with a single layer of modular counting gates. In: Frid, A., Morozov, A., Rybalchenko, A., Wagner, K.W. (eds.) Computer Science - Theory and Applications. LNCS, vol. 5675, pp. 117–128. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  9. 9.
    Hansen, K.A., Podolskii, V.V.: Exact threshold circuits. In: Proceedings of the 25th Annual IEEE Conference on Computational Complexity, pp. 270–279. IEEE Computer Society, Los Alamitos (2010)Google Scholar
  10. 10.
    Harkins, R.C., Hitchcock, J.M.: Dimension, halfspaces, and the density of hard sets. In: Lin, G. (ed.) COCOON 2007. LNCS, vol. 4598, pp. 129–139. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  11. 11.
    Håstad, J.: On the size of weights for threshold gates. SIAM Journal on Discrete Mathematics 7(3), 484–492 (1994)MATHCrossRefMathSciNetGoogle Scholar
  12. 12.
    Hertz, J., Krogh, A., Palmer, R.G.: Introduction to the Theory of Neural Computation. Addison-Wesley Publishing Company, Reading (1991)Google Scholar
  13. 13.
    Muroga, S., Toda, I., Takasu, S.: Theory of majority decision elements. Journal of the Franklin Institute 271, 376–418 (1961)MATHCrossRefMathSciNetGoogle Scholar
  14. 14.
    Muroga, S.: Threshold Logic and its Applications. John Wiley & Sons, Inc., Chichester (1971)MATHGoogle Scholar
  15. 15.
    Parberry, I.: Circuit Complexity and Neural Networks. MIT Press, Cambridge (1994)MATHGoogle Scholar
  16. 16.
    Podolskii, V.V.: A uniform lower bound on weights of perceptrons. In: Hirsch, E.A., Razborov, A.A., Semenov, A., Slissenko, A. (eds.) Computer Science – Theory and Applications. LNCS, vol. 5010, pp. 261–272. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  17. 17.
    Podolskii, V.V.: Perceptrons of large weight. Problems of Information Transmission 45(1), 46–53 (2009)MATHCrossRefMathSciNetGoogle Scholar
  18. 18.
    Smith, D.R.: Bounds on the number of threshold functions. IEEE Transactions on Electronic Computers EC 15(6), 368–369 (1966)MATHCrossRefGoogle Scholar
  19. 19.
    Yajima, S., Ibaraki, T.: A lower bound on the number of threshold functions. IEEE Transactions on Electronic Computers EC 14(6), 926–929 (1965)MATHCrossRefGoogle Scholar
  20. 20.
    Ziegler, G.M.: Lectures on 0/1-polytopes. In: Kalai, G., Ziegler, G.M. (eds.) Polytopes - Combinatorics and Computation, DMV Seminar, vol. 29, pp. 1–43. Birkhäuser, Basel (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • László Babai
    • 1
  • Kristoffer Arnsfelt Hansen
    • 2
  • Vladimir V. Podolskii
    • 3
  • Xiaoming Sun
    • 4
  1. 1.The University of Chicago 
  2. 2.Aarhus University 
  3. 3.Steklov Mathematical Institute 
  4. 4.ITCSTsinghua University 

Personalised recommendations