Learning Curves and Bootstrap Estimates for Inference with Gaussian Processes: A Statistical Mechanics Study

Dorthe Malzahn, Manfred Opper

    Research output: Contribution to journalJournal articleResearchpeer-review

    38 Downloads (Pure)

    Abstract

    We employ the replica method of statistical physics to study the average case performance of learning systems. The new feature of our theory is that general distributions of data can be treated, which enables applications to real data. For a class of Bayesian prediction models which are based on Gaussian processes, we discuss Bootstrap estimates for learning curves.
    Original languageEnglish
    JournalComplexity
    Volume8
    Issue number4
    Pages (from-to)57-63
    ISSN1076-2787
    Publication statusPublished - 2003

    Cite this

    @article{ec5f49f831914c5e9ad9473b41647951,
    title = "Learning Curves and Bootstrap Estimates for Inference with Gaussian Processes: A Statistical Mechanics Study",
    abstract = "We employ the replica method of statistical physics to study the average case performance of learning systems. The new feature of our theory is that general distributions of data can be treated, which enables applications to real data. For a class of Bayesian prediction models which are based on Gaussian processes, we discuss Bootstrap estimates for learning curves.",
    keywords = "variational methods, Bootstrap, learning curves, statistical physics, Gaussian processes",
    author = "Dorthe Malzahn and Manfred Opper",
    year = "2003",
    language = "English",
    volume = "8",
    pages = "57--63",
    journal = "Complexity",
    issn = "1076-2787",
    publisher = "JohnWiley & Sons, Inc.",
    number = "4",

    }

    Learning Curves and Bootstrap Estimates for Inference with Gaussian Processes: A Statistical Mechanics Study. / Malzahn, Dorthe; Opper, Manfred.

    In: Complexity, Vol. 8, No. 4, 2003, p. 57-63.

    Research output: Contribution to journalJournal articleResearchpeer-review

    TY - JOUR

    T1 - Learning Curves and Bootstrap Estimates for Inference with Gaussian Processes: A Statistical Mechanics Study

    AU - Malzahn, Dorthe

    AU - Opper, Manfred

    PY - 2003

    Y1 - 2003

    N2 - We employ the replica method of statistical physics to study the average case performance of learning systems. The new feature of our theory is that general distributions of data can be treated, which enables applications to real data. For a class of Bayesian prediction models which are based on Gaussian processes, we discuss Bootstrap estimates for learning curves.

    AB - We employ the replica method of statistical physics to study the average case performance of learning systems. The new feature of our theory is that general distributions of data can be treated, which enables applications to real data. For a class of Bayesian prediction models which are based on Gaussian processes, we discuss Bootstrap estimates for learning curves.

    KW - variational methods

    KW - Bootstrap

    KW - learning curves

    KW - statistical physics

    KW - Gaussian processes

    M3 - Journal article

    VL - 8

    SP - 57

    EP - 63

    JO - Complexity

    JF - Complexity

    SN - 1076-2787

    IS - 4

    ER -