2006
NeurIPS
NeurIPS 2006
PAC-Bayes Bounds for the Risk of the Majority Vote and the Variance of the Gibbs Classifier
Abstract
We propose new PAC-Bayes bounds for the risk of the weighted majority vote that depend on the mean and variance of the error of its associated Gibbs classifier. We show that these bounds can be smaller than the risk of the Gibbs classifier and can be arbitrarily close to zero even if the risk of the Gibbs classifier is close to 1/2. Moreover, we show that these bounds can be uniformly estimated on the training data for all possible posteriors Q. Moreover, they can be improved by using a large sample of unlabelled data.
🚀
Conference Pioneer
- NeurIPS 2006
📈
Trend Setter
- Statistics
🧭
Keyword Pioneer
- majority vote
🐣
Hot Topic Early Bird
- ensemble learning
Topics
Artificial Intelligence > Bayesian & Probabilistic > Bayesian Learning
Machine Learning > Optimization & Theory > Bayesian Inference
Machine Learning > Optimization & Theory > Learning Theory
Machine Learning > Optimization & Theory > Statistical Learning
Machine Learning > Bayesian & Probabilistic > Bayesian Learning
Machine Learning > Optimization & Theory > Statistics
Artificial Intelligence > Bayesian & Probabilistic > Bayesian Inference