A position paper arguing that narrow, puzzle-solving explanations of deep learning edge case phenomena are low-value, and that these phenomena should instead be used to stress-test broad explanatory theories.
Grokking Beyond Neural Networks: An Empirical Exploration with Model Complexity
1 Pith paper cite this work. Polarity classification is still indexing.
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 grokking on algorithmic datasets via the addition of dimensions containing spurious information. The presence of the phenomenon in non-neural architectures shows that grokking is not restricted to settings considered in current theoretical and empirical studies. Instead, grokking may be possible in any model where solution search is guided by complexity and error.
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Not All Explanations for Deep Learning Phenomena Are Equally Valuable
A position paper arguing that narrow, puzzle-solving explanations of deep learning edge case phenomena are low-value, and that these phenomena should instead be used to stress-test broad explanatory theories.