中文
相关论文

相关论文: Information-Theoretic Progress Measures reveal Gro…

200 篇论文

Grokking is a phenomenon where a model trained on an algorithmic task first overfits but, then, after a large amount of additional training, undergoes a phase transition to generalize perfectly. We empirically study the internal structure…

机器学习 · 计算机科学 2023-03-22 William Merrill , Nikolaos Tsilivis , Aman Shukla

Delayed generalization, termed grokking, in a machine learning calculation occurs when the increase in test accuracy is delayed relative to the training accuracy. This paper examines grokking in the context of a dense neural network trained…

无序系统与神经网络 · 物理学 2026-02-06 Karolina Hutchison , David Yevick

Neural networks often exhibit emergent behavior, where qualitatively new capabilities arise from scaling up the amount of parameters, training data, or training steps. One approach to understanding emergence is to find continuous…

机器学习 · 计算机科学 2023-10-23 Neel Nanda , Lawrence Chan , Tom Lieberum , Jess Smith , Jacob Steinhardt

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…

机器学习 · 计算机科学 2024-05-29 Zhangchen Zhou , Yaoyu Zhang , Zhi-Qin John Xu

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. Subsequent…

机器学习 · 计算机科学 2024-12-17 Hu Qiye , Zhou Hao , Yu RuoXi

We demonstrate the existence of a complexity phase transition in neural networks by studying the grokking phenomenon, where networks suddenly transition from memorization to generalization long after overfitting their training data. To…

机器学习 · 计算机科学 2025-08-22 Branton DeMoss , Silvia Sapora , Jakob Foerster , Nick Hawes , Ingmar Posner

Grokking, a phenomenon where machine learning models generalize long after overfitting, has been primarily observed and studied in algorithmic tasks. This paper explores grokking in real-world datasets using deep neural networks for…

机器学习 · 计算机科学 2024-06-21 Satvik Golechha

Grokking is a intriguing phenomenon in machine learning where a neural network, after many training iterations with negligible improvement in generalization, suddenly achieves high accuracy on unseen data. By working in the quantum-inspired…

We propose that the grokking phenomenon, where the train loss of a neural network decreases much earlier than its test loss, can arise due to a neural network transitioning from lazy training dynamics to a rich, feature learning regime. To…

机器学习 · 统计学 2024-04-12 Tanishq Kumar , Blake Bordelon , Samuel J. Gershman , Cengiz Pehlevan

''Grokking'' is a phenomenon where a neural network first memorizes training data and generalizes poorly, but then suddenly transitions to near-perfect generalization after prolonged training. While intriguing, this delayed generalization…

机器学习 · 计算机科学 2025-04-21 Zhiwei Xu , Zhiyu Ni , Yixin Wang , Wei Hu

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…

机器学习 · 统计学 2024-02-06 Noam Levi , Alon Beck , Yohai Bar-Sinai

Grokking, or delayed generalization, is an intriguing learning phenomenon where test set loss decreases sharply only after a model's training set loss has converged. This challenges conventional understanding of the training dynamics in…

机器学习 · 计算机科学 2025-02-05 Breno W. Carvalho , Artur S. d'Avila Garcez , Luís C. Lamb , Emílio Vital Brazil

Neural network grokking -- the abrupt memorization-to-generalization transition -- challenges our understanding of learning dynamics. Through finite-size scaling of gradient avalanche dynamics across eight model scales, we find that…

机器学习 · 计算机科学 2026-04-07 Ping Wang

The training dynamics of deep neural networks often defy expectations, even as these models form the foundation of modern machine learning. Two prominent examples are grokking, where test performance improves abruptly long after the…

机器学习 · 计算机科学 2026-01-28 Keitaro Sakamoto , Issei Sato

We discuss two solvable grokking (generalisation beyond overfitting) models in a rule learning scenario. We show that grokking is a phase transition and find exact analytic expressions for the critical exponents, grokking probability, and…

统计力学 · 物理学 2022-10-28 Bojan Žunkovič , Enej Ilievski

Grokking, referring to the abrupt improvement in test accuracy after extended overfitting, offers valuable insights into the mechanisms of model generalization. Existing researches based on progress measures imply that grokking relies on…

机器学习 · 计算机科学 2025-04-15 Zihan Gu , Ruoyu Chen , Hua Zhang , Yue Hu , Xiaochun Cao

Grokking refers to delayed generalization in which the increase in test accuracy of a neural network occurs appreciably after the improvement in training accuracy This paper introduces several practical metrics including variance under…

机器学习 · 计算机科学 2025-07-17 Ahmed Salah , David Yevick

Grokking, a delayed generalization in neural networks after perfect training performance, has been observed in Transformers and MLPs, but the components driving it remain underexplored. We show that embeddings are central to grokking:…

机器学习 · 计算机科学 2025-05-22 H. V. AlquBoj , Hilal AlQuabeh , Velibor Bojkovic , Munachiso Nwadike , Kentaro Inui

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 phenomenon through the…

机器学习 · 计算机科学 2024-02-05 Zhiquan Tan , Weiran Huang

A key property of deep neural networks (DNNs) is their ability to learn new features during training. This intriguing aspect of deep learning stands out most clearly in recently reported Grokking phenomena. While mainly reflected as a…

机器学习 · 统计学 2024-05-07 Noa Rubin , Inbar Seroussi , Zohar Ringel
‹ 上一页 1 2 3 10 下一页 ›