Grokking is a phenomenon when a neural network suddenly learns a pattern in the dataset and jumps from random chance generalization to perfect generalization very suddenly. This paper demonstrates grokking on small algorithmic datasets where a network has to fill in binary tables. Interestingly, the learned latent spaces show an emergence of the underlying binary operations that the data were created with.
0:00 - Intro & Overview
1:40 - The Grokking Phenomenon
3:50 - Related: Double Descent
7:50 - Binary Operations Datasets
11:45 - What quantities influence grokking?
15:40 - Learned Emerging Structure
17:35 - The role of smoothness
21:30 - Simple explanations win
24:30 - Why does weight decay encourage simplicity?
26:40 - Appendix
28:55 - Conclusion & Comments
In this paper we propose to study generalization of neural networks on small algorithmically generated datasets. In this setting, questions about data efficiency, memorization, generalization, and speed of learning can be studied in great detail. In some situations we show that neural networks learn through a process of “grokking” a pattern in the data, improving generalization performance from random chance level to perfect generalization, and that this improvement in generalization can happen well past the point of overfitting. We also study generalization as a function of dataset size and find that smaller datasets require increasing amounts of optimization for generalization. We argue that these datasets provide a fertile ground for studying a poorly understood aspect of deep learning: generalization of overparametrized neural networks beyond memorization of the finite training dataset.
Authors: Alethea Power, Yuri Burda, Harri Edwards, Igor Babuschkin & Vedant Misra