The Central Classifier Bound - A New Error Bound for the Classifier Chosen by Early Stopping

Abstract

Training with early stopping is the following process. Partition the in sample data into training and validation sets Begin with a random classifier g_(1-). Use an iterative method to decrease the error rate on the training data. Record the classifier at each iteration producing a series of snapshots g_1....g_M. Evaluate the error rate of each snapshot over the validation data. Deliver a minimum validation error classifier. g^* as the result of training.