Learning Boolean Functions via the Fourier Transform

  • Yishay Mansour


The importance of using the “right” representation of a function in order to “approximate” it has been widely recognized. The Fourier Transform representation of a function is a classic representation which is widely used to approximate real functions (i.e. functions whose inputs are real numbers). However, the Fourier Transform representation for functions whose inputs are boolean has been far less studied. On the other hand it seems that the Fourier Transform representation can be used to learn many classes of boolean functions.


Decision Tree Boolean Function Fourier Coefficient Conjunctive Normal Form Disjunctive Normal Form 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [Ajt83]
    M. Ajtai. formulae on finite structure. Annals of Pure and Applied Logic, 24:1–48, 1983.MathSciNetzbMATHCrossRefGoogle Scholar
  2. [AM91]
    William Aiello and Milena Mihail. Learning the fourier spectrum of probabilistic lists and trees. In Proceedings SODA 91, pages 291–299. ACM, Jan 1991.Google Scholar
  3. [Bel92]
    Mihir Bellare. A technique for upper bounding the spectral norm with applications to learning. In 5th Annual Workshop on Computational Learning Theory, pages 62–70, July 1992.Google Scholar
  4. [BHO90]
    Y. Brandman, J. Hennessy, and A. Orlitsky. A spectral lower bound technique for the size of decision trees and two level circuits. IEEE Trans. on Computers., 39(2):282–287, 1990.CrossRefGoogle Scholar
  5. [Bru90]
    J. Bruck. Harmonic analysis of polynomial threshold functions. Siam J. on Disc. Math., 3(2): 168–177, May 1990.MathSciNetzbMATHCrossRefGoogle Scholar
  6. [BS90]
    J. Bruck and R. Smolensky. Polynomial threshold functions, AC° functions and spectral norms. In 31th Annual Symposium on Foundations of Computer Science, St. Louis, Missouri, pages 632–641, October 1990.Google Scholar
  7. [FJS91]
    Merrick L. Furst, Jeffrey C. Jackson, and Sean W. Smith. Improved learning of AC° functions. In 4th Annual Workshop on Computational Learning Theory, pages 317–325, August 1991.Google Scholar
  8. [FSS84]
    M. Furst, J. Saxe, and M. Sipser. Parity, circuits, and the polynomial time hierarchy. Mathematical Systems Theory, 17:13–27, 1984.MathSciNetzbMATHCrossRefGoogle Scholar
  9. [GL89]
    O. Goldreich and L. Levin. A hard-core predicate for all one-way functions. In Proc. 21st ACM Symposium on Theory of Computing, pages 25–32. ACM, 1989.Google Scholar
  10. [Has86]
    J. Hastad. Computational limitations for small depth circuits. MIT Press, 1986. Ph.D. thesis.Google Scholar
  11. [HR89]
    Torben Hagerup and Christine Rub. A guided tour to chernoff bounds. Info. Proc. Lett, 33:305–308, 1989.CrossRefGoogle Scholar
  12. [Kha93]
    Michael Kharitonov. Cryptographic hardness of distribution-specific learning. In Proceedings of STOC’ 93, pages 372–381. ACM, 1993.Google Scholar
  13. [KKL88]
    J. Kahn, G. Kalai, and N. Linial. The influence of variables on boolean functions. In 29 th Annual Symposium on Foundations of Computer Science, White Plains, New York, pages 68–80, October 1988.Google Scholar
  14. [KM91]
    E. Kushilevitz and Y. Mansour. Learning decision trees using the fourier spectrum. In Proceedings of the 23 rd Annual ACM Symposium on Theory of Computing, pages 455–464, May 1991. (To appear in Siam J. on ComputingGoogle Scholar
  15. [LMN89]
    N. Linial, Y. Mansour, and N. Nisan. Constant depth circuits, Fourier Transform and learnability. In 30 th Annual Symposium on Foundations of Computer Science, Research Triangle Park, NC, pages 574–579, October 1989.Google Scholar
  16. [Man92]
    Yishay Mansour. An O(n log n) learning algorithm for DNF under the uniform distribution. In Workshop on Computational Learning Theory, pages 53–61, July 1992.Google Scholar
  17. [Riv87]
    Ronald L. Rivest. Learning decision lists. Machine Learning, 2(3):229–246, 1987.Google Scholar
  18. [SB91]
    Kai-Yeung Siu and Jehoshua Bruck. On the power of threshold circuits with small weights. Siam J. on Disc. Math., 4(3):423–435, Aug 1991.MathSciNetzbMATHCrossRefGoogle Scholar
  19. [Yao85]
    A. C. Yao. Separating the polynomial-time hierarchy by oracles. In 26th Annual Symposium on Foundations of Computer Science, Portland, Oregon, pages 1–10, October 1985.Google Scholar

Copyright information

© Springer Science+Business Media New York 1994

Authors and Affiliations

  • Yishay Mansour
    • 1
  1. 1.Computer Science DepartmentTel Aviv UniversityTel AvivIsrael

Personalised recommendations