Abstract-A new class of information-theoretic divergence measures based on the Shannon entropy is introduced. Unlike the well-known Kullback divergences, the new measures do not require the condition of absolute continuity to be satisfied by the probability distributions in-volved. More importantly

based on the minimization of the proposed bound. Doing so, we seek for a ρ-weighted majority vote that takes into account a trade-off between three quantities. The first two quantities being, as usual in the PAC-Bayesian ap-

. Recently Langford and Shawe-Taylor proved a dimensionindependent unit-norm margin bound using a relatively simple PAC-Bayesian argument. Unfortunately, the Langford-Shawe-Taylor bound is stated in a variational form making direct comparison to fat-shattering bounds difficult. This paper provides

There exist many different generalization error bounds for classification. Each of these bounds contains an improvement over the others for certain situations. Our goal is to combine these different improvements into a single bound. In particular we combine the PAC-Bayes approach introduced by Mc

solution to the variational problem implicit in the Langford-Shawe-Taylor bound and shows that the PAC-Bayesian margin bounds are significantly tighter. Because a PAC-Bayesian bound is derived from a particular prior distribution over hypotheses, a PAC-Bayesian margin bound also seems to provide insight

We present a bound on the generalisation error of linear classifiers in terms of a refined margin quantity on the training sample. The result is obtained in a PAC-Bayesian framework and is based on geometrical arguments in the space of linear classifiers. The new bound constitutes an exponential

We develop a scoring and classification procedure based on the PAC-Bayesian ap-proach and the AUC (Area Under Curve) criterion. We focus initially on the class of linear score functions. We derive PAC-Bayesian non-asymptotic bounds for two types of prior for the score parameters: a Gaussian prior

improvements into a single bound. In particular we combine the PAC-Bayes approach introduced by McAllester (1998), which is interesting for randomized predictions, with the optimal union bound provided by the generic chaining technique developed by Fernique and Talagrand (see Talagrand, 1996), in a way

We derive PAC-Bayesian generalization bounds for supervised and unsupervised learning models based on clustering, such as co-clustering, matrix tri-factorization, graphical models, graph clustering, and pairwise clustering. 1 We begin with the analysis of co-clustering, which is a widely used

The common method to understand and improve classification rules is to prove bounds on the generalization error. Here we provide localized data-based PAC-bounds for the di#erence between the risk of any two randomized estimators. We derive from these bounds two types of algorithms: the first one