Grokking Beyond Neural Networks: An Empirical Exploration with Model Complexity

arXiv:2310.17247v2 Announce Type: replace
Abstract: In some settings neural networks exhibit a phenomenon known as \textit{grokking}, where they achieve perfect or near-perfect accuracy on the validation set long after the same performance has been achieved on the training set. In this paper, we discover that grokking is not limited to neural networks but occurs in other settings such as Gaussian process (GP) classification, GP regression, linear regression and Bayesian neural networks. We also uncover a mechanism by which to induce …

abstract accuracy arxiv beyond complexity cs.lg exploration near networks neural networks paper performance set stat.ml training type validation