Learning with membership queries to minimize prediction error

Yoshifumi Ukita, Toshiyasu Matsushima, Shigeichi Hirasawa

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    In this paper, we consider the problem to predict the class of an unknown sample after learning from queries. We propose to evaluate a learning algorithm by a loss function for the prediction under a constraint. In this paper, the error probability for the prediction and the number of queries is defined as the loss function and the constraint, respectively. Then our objective is to minimize the error probability, the error probability is determined by what presentation order for instances to query and how to predict. Since the optimal prediction has been shown in previous researches, we only have to select the optimal presentation order for instances to query. We propose a lower bound used in the branch-and-bound algorithm to select the optimal presentation order for instances. Lastly, we show the efficiency of the algorithm using the derived lower bound by numerical computation.

    Original languageEnglish
    Title of host publicationProceedings of the IEEE International Conference on Systems, Man and Cybernetics
    Editors Anon
    PublisherIEEE
    Pages4412-4417
    Number of pages6
    Volume5
    Publication statusPublished - 1997
    EventProceedings of the 1997 IEEE International Conference on Systems, Man, and Cybernetics. Part 1 (of 5) - Orlando, FL, USA
    Duration: 1997 Oct 121997 Oct 15

    Other

    OtherProceedings of the 1997 IEEE International Conference on Systems, Man, and Cybernetics. Part 1 (of 5)
    CityOrlando, FL, USA
    Period97/10/1297/10/15

    Fingerprint

    Learning algorithms
    Error probability

    ASJC Scopus subject areas

    • Hardware and Architecture
    • Control and Systems Engineering

    Cite this

    Ukita, Y., Matsushima, T., & Hirasawa, S. (1997). Learning with membership queries to minimize prediction error. In Anon (Ed.), Proceedings of the IEEE International Conference on Systems, Man and Cybernetics (Vol. 5, pp. 4412-4417). IEEE.

    Learning with membership queries to minimize prediction error. / Ukita, Yoshifumi; Matsushima, Toshiyasu; Hirasawa, Shigeichi.

    Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. ed. / Anon. Vol. 5 IEEE, 1997. p. 4412-4417.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Ukita, Y, Matsushima, T & Hirasawa, S 1997, Learning with membership queries to minimize prediction error. in Anon (ed.), Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. vol. 5, IEEE, pp. 4412-4417, Proceedings of the 1997 IEEE International Conference on Systems, Man, and Cybernetics. Part 1 (of 5), Orlando, FL, USA, 97/10/12.
    Ukita Y, Matsushima T, Hirasawa S. Learning with membership queries to minimize prediction error. In Anon, editor, Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. Vol. 5. IEEE. 1997. p. 4412-4417
    Ukita, Yoshifumi ; Matsushima, Toshiyasu ; Hirasawa, Shigeichi. / Learning with membership queries to minimize prediction error. Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. editor / Anon. Vol. 5 IEEE, 1997. pp. 4412-4417
    @inproceedings{0ca38a8d69254ffa8107eea342eb20d4,
    title = "Learning with membership queries to minimize prediction error",
    abstract = "In this paper, we consider the problem to predict the class of an unknown sample after learning from queries. We propose to evaluate a learning algorithm by a loss function for the prediction under a constraint. In this paper, the error probability for the prediction and the number of queries is defined as the loss function and the constraint, respectively. Then our objective is to minimize the error probability, the error probability is determined by what presentation order for instances to query and how to predict. Since the optimal prediction has been shown in previous researches, we only have to select the optimal presentation order for instances to query. We propose a lower bound used in the branch-and-bound algorithm to select the optimal presentation order for instances. Lastly, we show the efficiency of the algorithm using the derived lower bound by numerical computation.",
    author = "Yoshifumi Ukita and Toshiyasu Matsushima and Shigeichi Hirasawa",
    year = "1997",
    language = "English",
    volume = "5",
    pages = "4412--4417",
    editor = "Anon",
    booktitle = "Proceedings of the IEEE International Conference on Systems, Man and Cybernetics",
    publisher = "IEEE",

    }

    TY - GEN

    T1 - Learning with membership queries to minimize prediction error

    AU - Ukita, Yoshifumi

    AU - Matsushima, Toshiyasu

    AU - Hirasawa, Shigeichi

    PY - 1997

    Y1 - 1997

    N2 - In this paper, we consider the problem to predict the class of an unknown sample after learning from queries. We propose to evaluate a learning algorithm by a loss function for the prediction under a constraint. In this paper, the error probability for the prediction and the number of queries is defined as the loss function and the constraint, respectively. Then our objective is to minimize the error probability, the error probability is determined by what presentation order for instances to query and how to predict. Since the optimal prediction has been shown in previous researches, we only have to select the optimal presentation order for instances to query. We propose a lower bound used in the branch-and-bound algorithm to select the optimal presentation order for instances. Lastly, we show the efficiency of the algorithm using the derived lower bound by numerical computation.

    AB - In this paper, we consider the problem to predict the class of an unknown sample after learning from queries. We propose to evaluate a learning algorithm by a loss function for the prediction under a constraint. In this paper, the error probability for the prediction and the number of queries is defined as the loss function and the constraint, respectively. Then our objective is to minimize the error probability, the error probability is determined by what presentation order for instances to query and how to predict. Since the optimal prediction has been shown in previous researches, we only have to select the optimal presentation order for instances to query. We propose a lower bound used in the branch-and-bound algorithm to select the optimal presentation order for instances. Lastly, we show the efficiency of the algorithm using the derived lower bound by numerical computation.

    UR - http://www.scopus.com/inward/record.url?scp=0031363145&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=0031363145&partnerID=8YFLogxK

    M3 - Conference contribution

    AN - SCOPUS:0031363145

    VL - 5

    SP - 4412

    EP - 4417

    BT - Proceedings of the IEEE International Conference on Systems, Man and Cybernetics

    A2 - Anon, null

    PB - IEEE

    ER -