A rationale from frequency perspective for grokking in training neural network

24 May 2024

Papers citing "A rationale from frequency perspective for grokking in training neural network"

4 / 4 papers shown

Title
Beyond the Next Token: Towards Prompt-Robust Zero-Shot Classification via Efficient Multi-Token Prediction Junlang Qian Zixiao Zhu Hanzhang Zhou Zijian Feng Zepeng Zhai K. Mao AAML VLM 38 0 0 04 Apr 2025
Do We Always Need the Simplicity Bias? Looking for Optimal Inductive Biases in the Wild Damien Teney Liangze Jiang Florin Gogianu Ehsan Abbasnejad 85 0 0 13 Mar 2025
Omnigrok: Grokking Beyond Algorithmic Data Ziming Liu Eric J. Michaud Max Tegmark 54 76 0 03 Oct 2022
Spectrum Dependent Learning Curves in Kernel Regression and Wide Neural Networks Blake Bordelon Abdulkadir Canatar C. Pehlevan 131 199 0 07 Feb 2020