The Hybrid Bootstrap: A Drop-in Replacement for Dropout
This is an incremental improvement to dropout regularization for machine learning practitioners.
The paper introduces the hybrid bootstrap, a regularization technique that resamples features from other training points instead of zeroing them like dropout, and demonstrates it offers superior performance to dropout across various models including CNNs and tree-based methods.
Regularization is an important component of predictive model building. The hybrid bootstrap is a regularization technique that functions similarly to dropout except that features are resampled from other training points rather than replaced with zeros. We show that the hybrid bootstrap offers superior performance to dropout. We also present a sampling based technique to simplify hyperparameter choice. Next, we provide an alternative sampling technique for convolutional neural networks. Finally, we demonstrate the efficacy of the hybrid bootstrap on non-image tasks using tree-based models.