Grokking in Linear Estimators -- A Solvable Model that Groks without Understanding
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Keywords: Grokking, Random Matrix Theory, Linear Regression, Representation Learning
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.
TL;DR: We present and analyze a solvable linear estimation model which exhibits grokking. We find that late generalization increase may not imply a transition from "memorization" to "understanding", but can simply be an artifact of the accuracy measure.
Abstract: Grokking is the intriguing phenomenon where a model learns to generalize long after it has fit the training data.
We show both analytically and numerically that grokking can surprisingly occur in linear networks performing linear tasks in a simple teacher-student setup. In this setting, the full training dynamics is derived in terms of the expected training and generalization data covariance matrix. We present exact predictions on how the grokking time depends on input and output dimensionality, train sample size, regularization, and network parameters initialization.
The key findings are that late generalization increase may not imply a transition from "memorization" to "understanding", but can simply be an artifact of the accuracy measure.
We provide empirical verification for these propositions, along with preliminary results indicating that some predictions also hold for deeper networks, with non-linear activations.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Primary Area: learning theory
Submission Number: 1932
Loading