Optimally Combining Classifiers Using Unlabeled Data
Abstract
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.
Cite
Text
Balsubramani and Freund. "Optimally Combining Classifiers Using Unlabeled Data." Annual Conference on Computational Learning Theory, 2015.Markdown
[Balsubramani and Freund. "Optimally Combining Classifiers Using Unlabeled Data." Annual Conference on Computational Learning Theory, 2015.](https://mlanthology.org/colt/2015/balsubramani2015colt-optimally/)BibTeX
@inproceedings{balsubramani2015colt-optimally,
title = {{Optimally Combining Classifiers Using Unlabeled Data}},
author = {Balsubramani, Akshay and Freund, Yoav},
booktitle = {Annual Conference on Computational Learning Theory},
year = {2015},
pages = {211-225},
url = {https://mlanthology.org/colt/2015/balsubramani2015colt-optimally/}
}