EERO: Early Exit with Reject Option for Efficient Classification with limited budget

The increasing complexity of advanced machine learning models requires innovative approaches to manage computational resources effectively. One such method is the Early Exit strategy, which allows for adaptive computation by providing a mechanism to shorten the processing path for simpler data instances. In this paper, we propose EERO, a new methodology to translate the problem of early exiting to a problem of using multiple classifiers with reject option in order to better select the exiting head for each instance. We …

advanced budget classification complexity computation computational cs.lg data exit instances machine machine learning machine learning models paper path processing resources stat.ml strategy