How many queries are needed to learn?

Lisa Hellerstein, Krishnan Pillaipakkamnatt, Vijay Raghavan, Dawn Wilkins

    Research output: Contribution to journalArticle

    Abstract

    We investigate the query complexity of exact learning in the membership and (proper) equivalence query model. We give a complete characterization of concept classes that are learnable with a polynomial number of polynomial sized queries in this model. We give applications of this characterization, including results on learning a natural subclass of DNF formulas, and on learning with membership queries alone. Query complexity has previously been used to prove lower bounds on the time complexity of exact learning. We show a new relationship between query complexity and time complexity in exact learning: If any "honest" class is exactly and properly learnable with polynomial query complexity, but not learnable in polynomial time, then P ≠ NP. In particular, we show that an honest class is exactly polynomial-query learnable if and only if it is learnable using an oracle for Σ4p.

    Original languageEnglish (US)
    Pages (from-to)840-862
    Number of pages23
    JournalJournal of the ACM
    Volume43
    Issue number5
    StatePublished - Sep 1996

    Fingerprint

    Query Complexity
    Polynomials
    Query
    Time Complexity
    Polynomial
    Polynomial Complexity
    Polynomial time
    Equivalence
    Learning
    Lower bound
    If and only if
    Model
    Class

    ASJC Scopus subject areas

    • Computational Theory and Mathematics
    • Computer Graphics and Computer-Aided Design
    • Hardware and Architecture
    • Information Systems
    • Software
    • Theoretical Computer Science

    Cite this

    Hellerstein, L., Pillaipakkamnatt, K., Raghavan, V., & Wilkins, D. (1996). How many queries are needed to learn? Journal of the ACM, 43(5), 840-862.

    How many queries are needed to learn? / Hellerstein, Lisa; Pillaipakkamnatt, Krishnan; Raghavan, Vijay; Wilkins, Dawn.

    In: Journal of the ACM, Vol. 43, No. 5, 09.1996, p. 840-862.

    Research output: Contribution to journalArticle

    Hellerstein, L, Pillaipakkamnatt, K, Raghavan, V & Wilkins, D 1996, 'How many queries are needed to learn?', Journal of the ACM, vol. 43, no. 5, pp. 840-862.
    Hellerstein L, Pillaipakkamnatt K, Raghavan V, Wilkins D. How many queries are needed to learn? Journal of the ACM. 1996 Sep;43(5):840-862.
    Hellerstein, Lisa ; Pillaipakkamnatt, Krishnan ; Raghavan, Vijay ; Wilkins, Dawn. / How many queries are needed to learn?. In: Journal of the ACM. 1996 ; Vol. 43, No. 5. pp. 840-862.
    @article{571a46b5a81a4d34be6822883297815c,
    title = "How many queries are needed to learn?",
    abstract = "We investigate the query complexity of exact learning in the membership and (proper) equivalence query model. We give a complete characterization of concept classes that are learnable with a polynomial number of polynomial sized queries in this model. We give applications of this characterization, including results on learning a natural subclass of DNF formulas, and on learning with membership queries alone. Query complexity has previously been used to prove lower bounds on the time complexity of exact learning. We show a new relationship between query complexity and time complexity in exact learning: If any {"}honest{"} class is exactly and properly learnable with polynomial query complexity, but not learnable in polynomial time, then P ≠ NP. In particular, we show that an honest class is exactly polynomial-query learnable if and only if it is learnable using an oracle for Σ4p.",
    author = "Lisa Hellerstein and Krishnan Pillaipakkamnatt and Vijay Raghavan and Dawn Wilkins",
    year = "1996",
    month = "9",
    language = "English (US)",
    volume = "43",
    pages = "840--862",
    journal = "Journal of the ACM",
    issn = "0004-5411",
    publisher = "Association for Computing Machinery (ACM)",
    number = "5",

    }

    TY - JOUR

    T1 - How many queries are needed to learn?

    AU - Hellerstein, Lisa

    AU - Pillaipakkamnatt, Krishnan

    AU - Raghavan, Vijay

    AU - Wilkins, Dawn

    PY - 1996/9

    Y1 - 1996/9

    N2 - We investigate the query complexity of exact learning in the membership and (proper) equivalence query model. We give a complete characterization of concept classes that are learnable with a polynomial number of polynomial sized queries in this model. We give applications of this characterization, including results on learning a natural subclass of DNF formulas, and on learning with membership queries alone. Query complexity has previously been used to prove lower bounds on the time complexity of exact learning. We show a new relationship between query complexity and time complexity in exact learning: If any "honest" class is exactly and properly learnable with polynomial query complexity, but not learnable in polynomial time, then P ≠ NP. In particular, we show that an honest class is exactly polynomial-query learnable if and only if it is learnable using an oracle for Σ4p.

    AB - We investigate the query complexity of exact learning in the membership and (proper) equivalence query model. We give a complete characterization of concept classes that are learnable with a polynomial number of polynomial sized queries in this model. We give applications of this characterization, including results on learning a natural subclass of DNF formulas, and on learning with membership queries alone. Query complexity has previously been used to prove lower bounds on the time complexity of exact learning. We show a new relationship between query complexity and time complexity in exact learning: If any "honest" class is exactly and properly learnable with polynomial query complexity, but not learnable in polynomial time, then P ≠ NP. In particular, we show that an honest class is exactly polynomial-query learnable if and only if it is learnable using an oracle for Σ4p.

    UR - http://www.scopus.com/inward/record.url?scp=0030230237&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=0030230237&partnerID=8YFLogxK

    M3 - Article

    AN - SCOPUS:0030230237

    VL - 43

    SP - 840

    EP - 862

    JO - Journal of the ACM

    JF - Journal of the ACM

    SN - 0004-5411

    IS - 5

    ER -