Skip to main content

Testing (Subclasses of) Halfspaces

  • Chapter
Property Testing

Part of the book series: Lecture Notes in Computer Science ((LNTCS,volume 6390))

  • 1085 Accesses

Abstract

We address the problem of testing whether a Boolean-valued function f is a halfspace, i.e. a function of the form f(x) = sgn(w . x − θ). We consider halfspaces over the continuous domain Rn (endowed with the standard multivariate Gaussian distribution) as well as halfspaces over the Boolean cube { − 1,1}n (endowed with the uniform distribution). In both cases we give an algorithm that distinguishes halfspaces from functions that are ε-far from any halfspace using only poly\((\frac{1}{\epsilon})\) queries, independent of the dimension n.

In contrast to the case of general halfspaces, we show that testing natural subclasses of halfspaces can be markedly harder; for the class of { − 1,1}-weight halfspaces, we show that a tester must make at least Ω(logn) queries. We complement this lower bound with an upper bound showing that \(O(\sqrt{n})\) queries suffice.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

eBook
USD 16.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 16.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Birkendorf, A., Dichterman, E., Jackson, J., Klasner, N., Simon, H.U.: On restricted-focus-of-attention learnability of Boolean functions. Machine Learning 30, 89–123 (1998)

    Article  MATH  Google Scholar 

  2. Block, H.: The Perceptron: a model for brain functioning. Reviews of Modern Physics 34, 123–135 (1962)

    Article  MathSciNet  MATH  Google Scholar 

  3. Chow, C.K.: On the characterization of threshold functions. In: Proceedings of the Symposium on Switching Circuit Theory and Logical Design (FOCS), pp. 34–38 (1961)

    Google Scholar 

  4. Diakonikolas, I., Lee, H., Matulef, K., Onak, K., Rubinfeld, R., Servedio, R., Wan, A.: Testing for concise representations. In: Proc. 48th Ann. Symposium on Computer Science (FOCS), pp. 549–558 (2007)

    Google Scholar 

  5. Fischer, E.: The art of uninformed decisions: A primer to property testing. Bulletin of the European Association for Theoretical Computer Science 75, 97–126 (2001)

    MathSciNet  MATH  Google Scholar 

  6. Fischer, E., Kindler, G., Ron, D., Safra, S., Samorodnitsky, A.: Testing juntas. In: Proceedings of the 43rd IEEE Symposium on Foundations of Computer Science, pp. 103–112 (2002)

    Google Scholar 

  7. Goldberg, P.: A Bound on the Precision Required to Estimate a Boolean Perceptron from its Average Satisfying Assignment. SIAM Journal on Discrete Mathematics 20, 328–343 (2006)

    Article  MathSciNet  MATH  Google Scholar 

  8. Goldreich, O., Goldwaser, S., Ron, D.: Property testing and its connection to learning and approximation. Journal of the ACM 45, 653–750 (1998)

    Article  MathSciNet  MATH  Google Scholar 

  9. Hajnal, A., Maass, W., Pudlak, P., Szegedy, M., Turan, G.: Threshold circuits of bounded depth. Journal of Computer and System Sciences 46, 129–154 (1993)

    Article  MathSciNet  MATH  Google Scholar 

  10. Hellerstein, L.: On generalized constraints and certificates. Discrete Mathematics 226(211-232) (2001)

    Google Scholar 

  11. Kulkarni, S., Mitter, S., Tsitsiklis, J.: Active learning using arbitrary binary valued queries. Machine Learning 11, 23–35 (1993)

    Article  MATH  Google Scholar 

  12. Matulef, K., Rubinfeld, R., Servedio, R.A., O’Donnell, R.: Testing {-1,1} - Weight Halfspaces. In: Dinur, I., Jansen, K., Naor, J., Rolim, J. (eds.) APPROX-RANDOM 2009. LNCS, vol. 5687, pp. 646–657. Springer, Heidelberg (2009)

    Google Scholar 

  13. Matulef, K., O’Donnell, R., Rubinfeld, R., Servedio, R.A.: Testing halfspaces. In: 20th Annual ACM-SIAM Symposium on Discrete Algorithms (SODA), pp. 256–264 (2009)

    Google Scholar 

  14. Minsky, M., Papert, S.: Perceptrons: an introduction to computational geometry. MIT Press, Cambridge (1968)

    MATH  Google Scholar 

  15. Novikoff, A.: On convergence proofs on perceptrons. In: Proceedings of the Symposium on Mathematical Theory of Automata, vol. XII, pp. 615–622 (1962)

    Google Scholar 

  16. Servedio, R.: Every linear threshold function has a low-weight approximator. Computational Complexity 16(2), 180–209 (2007)

    Article  MathSciNet  MATH  Google Scholar 

  17. Shawe-Taylor, J., Cristianini, N.: An introduction to support vector machines. Cambridge University Press, Cambridge (2000)

    MATH  Google Scholar 

  18. Yao, A.: On ACC and threshold circuits. In: Proceedings of the Thirty-First Annual Symposium on Foundations of Computer Science, pp. 619–627 (1990)

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2010 Springer-Verlag Berlin Heidelberg

About this chapter

Cite this chapter

Matulef, K., O’Donnell, R., Rubinfeld, R., Servedio, R. (2010). Testing (Subclasses of) Halfspaces. In: Goldreich, O. (eds) Property Testing. Lecture Notes in Computer Science, vol 6390. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-16367-8_27

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-16367-8_27

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-642-16366-1

  • Online ISBN: 978-3-642-16367-8

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics