To grok or not to grok: Disentangling generalization and memorization on corrupted algorithmic datasets

19 October 2023

Papers citing "To grok or not to grok: Disentangling generalization and memorization on corrupted algorithmic datasets"

6 / 6 papers shown

Title
Information-Theoretic Progress Measures reveal Grokking is an Emergent Phase Transition Kenzo Clauw S. Stramaglia Daniele Marinazzo 45 3 0 16 Aug 2024
Grokking phase transitions in learning local rules with gradient descent Bojan Žunkovič E. Ilievski 50 16 0 26 Oct 2022
Omnigrok: Grokking Beyond Algorithmic Data Ziming Liu Eric J. Michaud Max Tegmark 54 76 0 03 Oct 2022
Extracting Training Data from Large Language Models Nicholas Carlini Florian Tramèr Eric Wallace Matthew Jagielski Ariel Herbert-Voss ... Tom B. Brown D. Song Ulfar Erlingsson Alina Oprea Colin Raffel MLAU SILM 267 1,798 0 14 Dec 2020
Norm-Based Capacity Control in Neural Networks Behnam Neyshabur Ryota Tomioka Nathan Srebro 111 577 0 27 Feb 2015
Improving neural networks by preventing co-adaptation of feature detectors Geoffrey E. Hinton Nitish Srivastava A. Krizhevsky Ilya Sutskever Ruslan Salakhutdinov VLM 243 7,597 0 03 Jul 2012