Optimally Combining Classifiers Using Unlabeled Data
This work addresses the challenge of improving classification accuracy by optimally combining multiple classifiers, which is incremental as it builds on existing ensemble methods.
The paper tackles the problem of aggregating classifier ensembles for binary classification using a worst-case analysis in a transductive setting with unlabeled data, showing that a weighted combination can significantly outperform any single classifier.
We develop a worst-case analysis of aggregation of classifier ensembles for binary classification. The task of predicting to minimize error is formulated as a game played over a given set of unlabeled data (a transductive setting), where prior label information is encoded as constraints on the game. The minimax solution of this game identifies cases where a weighted combination of the classifiers can perform significantly better than any single classifier.