An approximate analytical approach to resampling averages

Dorthe Malzahn, M. Opper

    Research output: Contribution to journalJournal articleResearchpeer-review


    Using a novel reformulation, we develop a framework to compute approximate resampling data averages analytically. The method avoids multiple retraining of statistical models on the samples. Our approach uses a combination of the replica "trick" of statistical physics and the TAP approach for approximate Bayesian inference. We demonstrate our approach on regression with Gaussian processes. A comparison with averages obtained by Monte-Carlo sampling shows that our method achieves good accuracy.
    Original languageEnglish
    JournalJournal of Machine Learning Research
    Issue number6
    Pages (from-to)1151-1173
    Publication statusPublished - 2004


    • bootstrap
    • approximate inference
    • kernel machines
    • statistical physics
    • Gaussian processes

    Cite this