A PAC-Bayes Risk Bound for General Loss Functions
نویسندگان
چکیده
We provide a PAC-Bayesian bound for the expected loss of convex combinations of classifiers under a wide class of loss functions (which includes the exponential loss and the logistic loss). Our numerical experiments with Adaboost indicate that the proposed upper bound, computed on the training set, behaves very similarly as the true loss estimated on the testing set.
منابع مشابه
From PAC-Bayes Bounds to KL Regularization
We show that convex KL-regularized objective functions are obtained from a PAC-Bayes risk bound when using convex loss functions for the stochastic Gibbs classifier that upper-bound the standard zero-one loss used for the weighted majority vote. By restricting ourselves to a class of posteriors, that we call quasi uniform, we propose a simple coordinate descent learning algorithm to minimize th...
متن کاملTight Bounds for the Expected Risk of Linear Classifiers and PAC-Bayes Finite-Sample Guarantees
We analyze the expected risk of linear classifiers for a fixed weight vector in the “minimax” setting. That is, we analyze the worst-case risk among all data distributions with a given mean and covariance. We provide a simpler proof of the tight polynomial-tail bound for general random variables. For sub-Gaussian random variables, we derive a novel tight exponentialtail bound. We also provide n...
متن کاملPAC-Bayes-Empirical-Bernstein Inequality
We present a PAC-Bayes-Empirical-Bernstein inequality. The inequality is based on a combination of the PAC-Bayesian bounding technique with an Empirical Bernstein bound. We show that when the empirical variance is significantly smaller than the empirical loss the PAC-Bayes-Empirical-Bernstein inequality is significantly tighter than the PAC-Bayes-kl inequality of Seeger (2002) and otherwise it ...
متن کاملPAC-Bayes Risk Bounds for Stochastic Averages and Majority Votes of Sample-Compressed Classifiers
We propose a PAC-Bayes theorem for the sample-compression setting where each classifier is described by a compression subset of the training data and a message string of additional information. This setting, which is the appropriate one to describe many learning algorithms, strictly generalizes the usual data-independent setting where classifiers are represented only by data-independent message...
متن کاملA PAC-Bayes approach to the Set Covering Machine
We design a new learning algorithm for the Set Covering Machine from a PAC-Bayes perspective and propose a PAC-Bayes risk bound which is minimized for classifiers achieving a non trivial margin-sparsity trade-off.
متن کامل