Skip to main content

Learning with the Aid of an Oracle

1996; Bshouty, Cleve, Gavaldà, Kannan, Tamon

  • Reference work entry
Encyclopedia of Algorithms
  • 274 Accesses

Keywords and Synonyms

Oracles and queries that are sufficient for exact learning      

Problem Definition

In the exact learning model of Angluin [1], a learning algorithm A must discover an unknown function \( \mathsf{f} \colon \{0,1\}^{n} \rightarrow \{0,1\} \) that is a member of a known class C of Boolean functions. The learning algorithm can make at least one of the following types of queries about f:

  • Equivalence query \( { \mathsf{EQ}_{\mathsf{f}}(\mathsf{g}) } \), for a candidate function g: The reply is either “yes”, if \( { \mathsf{g} \Leftrightarrow \mathsf{f} } \), or a counterexample a with \( { \mathsf{g}(a) \neq \mathsf{f}(a) } \), otherwise.

  • Membership query \( { \mathsf{MQ}_{\mathsf{f}}(a) } \), for some \( { a \in \{0,1\}^{n} } \): The reply is the Boolean value \( { \mathsf{f}(a) } \).

  • Subset query \( { \mathsf{SubQ}_{\mathsf{f}}(\mathsf{g}) } \), for a candidate function g: The reply is “yes”, if \( { \mathsf{g} \Rightarrow \mathsf{f} } \), or a counterexample a with \( {...

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

Access this chapter

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 399.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Recommended Reading

  1. Angluin, D.: Queries and Concept Learning. Mach. Learn. 2, 319–342 (1988)

    Google Scholar 

  2. Angluin, D., Kharitonov, M.: When Won't Membership Queries Help? J. Comput. Syst. Sci. 50, 336–355 (1995)

    Google Scholar 

  3. Bshouty, N.H.: Exact Learning Boolean Function via the Monotone Theory. Inform. Comput. 123, 146–153 (1995)

    Article  MathSciNet  MATH  Google Scholar 

  4. Bshouty, N.H., Cleve, R., Gavaldà, R., Kannan, S., Tamon, C.: Oracles and Queries That Are Sufficient for Exact Learning. J. Comput. Syst. Sci. 52(3), 421–433 (1996)

    Article  MATH  Google Scholar 

  5. Gunopolous, D., Khardon, R., Mannila, H., Saluja, S., Toivonen, H., Sharma, R.S.: Discovering All Most Specific Sentences. ACM Trans. Database Syst. 28, 140–174 (2003)

    Article  Google Scholar 

  6. Jerrum, M.R., Valiant, L.G., Vazirani, V.V.: Random Generation of Combinatorial Structures from a Uniform Distribution. Theor. Comput. Sci. 43, 169–188 (1986)

    Article  MathSciNet  MATH  Google Scholar 

  7. Karp, R.M., Lipton, R.J.: Some Connections Between Nonuniform and Uniform Complexity Classes. In: Proc. 12th Ann. ACM Symposium on Theory of Computing, 1980, pp. 302–309

    Google Scholar 

  8. Klivans, A.R., Servedio, R.A.: Learning DNF in Time \( { 2^{\tilde{O}(n^{1/3})} } \). J. Comput. Syst. Sci. 68, 303–318 (2004)

    Article  MathSciNet  MATH  Google Scholar 

  9. Köbler, J., Watanabe, O.: New Collapse Consequences of NP Having Small Circuits. SIAM J. Comput. 28, 311–324 (1998)

    Article  MATH  Google Scholar 

  10. Littlestone, N.: Learning Quickly When Irrelevant Attributes Abound: A New Linear‐Threshold Algorithm. Mach. Learn. 2, 285–318 (1987)

    Google Scholar 

  11. Sipser, M.: A complexity theoretic approach to randomness. In: Proc. 15th Annual ACM Symposium on Theory of Computing, 1983, pp. 330–334

    Google Scholar 

  12. Stockmeyer, L.J.: On approximation algorithms for #P. SIAM J. Comput. 14, 849–861 (1985)

    Article  MathSciNet  MATH  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2008 Springer-Verlag

About this entry

Cite this entry

Tamon, C. (2008). Learning with the Aid of an Oracle. In: Kao, MY. (eds) Encyclopedia of Algorithms. Springer, Boston, MA. https://doi.org/10.1007/978-0-387-30162-4_193

Download citation

Publish with us

Policies and ethics