Главная

Liva Ralaivola

  1. PAC-Bayesian Generalization Bound on Confusion Matrix for Multi-Class Classification.

    Ср, 02/29/2012 - 15:01 — SomNambul
    Authors: Liva Ralaivola, Emilie Morvant, Sokol Koço
    Subjects: Machine Learning
    Abstract

    In this work, we propose a PAC-Bayes bound for the generalization risk of the
    Gibbs classifier in the multi-class classification framework. The novelty of
    our work is the critical use of the confusion matrix of a classifier as an
    error measure; this puts our contribution in the line of work aiming at dealing
    with performance measure that are richer than mere scalar criterion such as the
    misclassification rate.

  2. Stochastic Low-Rank Kernel Learning for Regression.

    Пт, 01/13/2012 - 15:01 — SomNambul
    Authors: Liva Ralaivola, Pierre Machart, Thomas Peel, Sandrine Anthoine, Hervé Glotin
    Subjects: Learning
    Abstract

    We present a novel approach to learn a kernel-based regression function. It
    is based on the useof conical combinations of data-based parameterized kernels
    and on a new stochastic convex optimization procedure of which we establish
    convergence guarantees. The overall learning procedure has the nice properties
    that a) the learned conical combination is automatically designed to perform
    the regression task at hand and b) the updates implicated by the optimization
    procedure are quite inexpensive.

  3. Chromatic PAC-Bayes Bounds for Non-IID Data: Applications to Ranking and Stationary \beta-Mixing Processes.

    Пт, 09/11/2009 - 19:13 — SomNambul
    Authors: Liva Ralaivola, Marie Szafranski, Guillaume Stempfel
    Subjects: Learning
    Abstract

    Pac-Bayes bounds are among the most accurate generalization bounds for
    classifiers learned from independently and identically distributed (IID) data,
    and it is particularly so for margin classifiers: there have been recent
    contributions showing how practical these bounds can be either to perform model
    selection (Ambroladze et al., 2007) or even to directly guide the learning of
    linear classifiers (Germain et al., 2009). However, there are many practical
    situations where the training data show some dependencies and where the
    traditional IID assumption does not hold.

Math-arch

RSS-материал