SADT: Combining Sharpness-Aware Minimization with Self-Distillation for Improved Model Generalization

1 code implementation • 1 Nov 2022 • Masud An-Nur Islam Fahim, Jani Boutellier

Methods for improving deep neural network training times and model generalizability consist of various data augmentation, regularization, and optimization approaches, which tend to be sensitive to hyperparameter settings and make reproducibility more challenging.

Data Augmentation