Grokking as Compression: A Nonlinear Complexity Perspective

9 October 2023

Papers citing "Grokking as Compression: A Nonlinear Complexity Perspective"

7 / 7 papers shown

Title
A Two-Phase Perspective on Deep Learning Dynamics Robert de Mello Koch Animik Ghosh 34 0 0 17 Apr 2025
Information-Theoretic Progress Measures reveal Grokking is an Emergent Phase Transition Kenzo Clauw S. Stramaglia Daniele Marinazzo 45 3 0 16 Aug 2024
Rethinking LLM Memorization through the Lens of Adversarial Compression Avi Schwarzschild Zhili Feng Pratyush Maini Zachary Chase Lipton J. Zico Kolter 39 38 0 23 Apr 2024
Mechanistic Interpretability for AI Safety -- A Review Leonard Bereska E. Gavves AI4CE 38 111 0 22 Apr 2024
Bridging Lottery Ticket and Grokking: Understanding Grokking from Inner Structure of Networks Gouki Minegishi Yusuke Iwasawa Yutaka Matsuo 11 3 0 30 Oct 2023
Grokking Beyond Neural Networks: An Empirical Exploration with Model Complexity Jack Miller Charles OÑeill Thang Bui 19 9 0 26 Oct 2023
Omnigrok: Grokking Beyond Algorithmic Data Ziming Liu Eric J. Michaud Max Tegmark 54 76 0 03 Oct 2022