Pseudo inputs for pairwise learning with Gaussian processes

Jens Brehm Nielsen, Bjørn Sand Jensen, Jan Larsen

    Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

    Abstract

    We consider learning and prediction of pairwise comparisons between instances. The problem is motivated from a perceptual view point, where pairwise comparisons serve as an effective and extensively used paradigm. A state-of-the-art method for modeling pairwise data in high dimensional domains is based on a classical pairwise probit likelihood imposed with a Gaussian process prior. While extremely flexible, this non-parametric method struggles with an inconvenient O(n3) scaling in terms of the n input instances which limits the method only to smaller problems. To overcome this, we derive a specific sparse extension of the classical pairwise likelihood using the pseudo-input formulation. The behavior of the proposed extension is demonstrated on a toy example and on two real-world data sets which outlines the potential gain and pitfalls of the approach. Finally, we discuss the relation to other similar approximations that have been applied in standard Gaussian process regression and classification problems such as FI(T)C and PI(T)C.
    Original languageEnglish
    Title of host publication2012 IEEE International Workshop on Machine Learning for Signal Processing (MLSP)
    Number of pages6
    PublisherIEEE
    Publication date2012
    ISBN (Print)978-1-4673-1024-6
    ISBN (Electronic)978-1-4673-1025-3
    DOIs
    Publication statusPublished - 2012
    Event2012 IEEE International Workshop on Machine Learning for Signal Processing (MLSP) - Santander, Spain
    Duration: 23 Oct 201226 Oct 2012
    http://mlsp2012.conwiz.dk/

    Conference

    Conference2012 IEEE International Workshop on Machine Learning for Signal Processing (MLSP)
    CountrySpain
    CitySantander
    Period23/10/201226/10/2012
    Internet address
    SeriesMachine Learning for Signal Processing
    ISSN1551-2541

    Fingerprint Dive into the research topics of 'Pseudo inputs for pairwise learning with Gaussian processes'. Together they form a unique fingerprint.

    Cite this