paper-with-me

Papers

A rationale from frequency perspective for grokking in training neural network

2024-05-24 · Zhangchen Zhou, Yaoyu Zhang, Zhi-Qin John Xu

Grokking is the phenomenon where neural networks NNs initially fit the training data and later generalize to the test data during training. In this paper, we empirically provide a frequency perspective to explain the emergence of this phenomenon in NNs. The core insight is that the networks initially learn the less salient frequency components present in the test data. We observe this phenomenon across both synthetic and real datasets, offering a novel viewpoint for elucidating the grokking phenomenon by characterizing it through the lens of frequency dynamics during the training process. Our empirical frequency-based analysis sheds new light on understanding the grokking phenomenon and its underlying mechanisms.

📄 PDF Abstract BibTeX arXiv:2405.17479

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Critical Data Size of Language Models from a Grokking Perspective

2024-01-19 · Xuekai Zhu, Yao Fu, BoWen Zhou, Zhouhan Lin

We explore the critical data size in language models, a threshold that marks a fundamental shift from quick memorization to slow generalization. We formalize the phase transition under the grokking configuration into the…

Language ModelingLanguage ModellingMemorization

Exploring Grokking: Experimental and Mechanistic Investigations

2024-12-14 · Hu Qiye, Zhou Hao, Yu RuoXi

The phenomenon of grokking in over-parameterized neural networks has garnered significant interest. It involves the neural network initially memorizing the training set with zero training error and near-random test error…

Predicting Grokking Long Before it Happens: A look into the loss landscape of models which grok

2023-06-23 · Pascal Jr. Tikeng Notsawo, Hattie Zhou, Mohammad Pezeshki, Irina Rish 외

This paper focuses on predicting the occurrence of grokking in neural networks, a phenomenon in which perfect generalization emerges long after signs of overfitting or memorization are observed. It has been reported that…

Memorization

Understanding Grokking Through A Robustness Viewpoint

2023-11-11 · Zhiquan Tan, Weiran Huang

Recently, an interesting phenomenon called grokking has gained much attention, where generalization occurs long after the models have initially overfitted the training data. We try to understand this seemingly strange ph…

A Basin-Selection Perspective on Grokking via Singular Learning Theory

2026-03-01 · Ben Cullen, Sergio Estan-Ruiz, Riya Danait, Jiayi Li arxiv

Grokking, the abrupt transition from memorization to generalisation after extended training, suggests the presence of competing solution basins with distinct statistical properties. We study this phenomenon through the l…