PAC-Bayes with Minimax for Confidence-Rated Transduction.
CoRR(2015)
摘要
We consider using an ensemble of binary classifiers for transductive prediction, when unlabeled test data are known in advance. We derive minimax optimal rules for confidence-rated prediction in this setting. By using PAC-Bayes analysis on these rules, we obtain data-dependent performance guarantees without distributional assumptions on the data. Our analysis techniques are readily extended to a setting in which the predictor is allowed to abstain.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络