English
Related papers

Related papers: Explaining Grokking and Information Bottleneck thr…

200 papers

Increasing the L2 regularization of Deep Neural Networks (DNNs) causes a first-order phase transition into the under-parametrized phase -- the so-called onset-of learning. We explain this transition via the scalar (Ricci) curvature of the…

Machine Learning · Computer Science 2025-08-29 Ibrahim Talha Ersoy , Karoline Wiesner

Grokking in modular arithmetic has established itself as the quintessential fruit fly experiment, serving as a critical domain for investigating the mechanistic origins of model generalization. Despite its significance, existing research…

Artificial Intelligence · Computer Science 2026-04-01 Junjie Zhang , Zhen Shen , Gang Xiong , Xisong Dong

Grokking-the phenomenon where validation accuracy of neural networks on modular addition of two integers rises long after training data has been memorized-has been characterized in previous works as producing sinusoidal input weight…

Machine Learning · Computer Science 2026-03-26 Anand Swaroop

Abrupt learning is a common phenomenon in recurrent neural networks (RNNs) trained on working memory tasks. In such cases, the networks develop transient slow regions in state space that extend the effective timescales of computation.…

Machine Learning · Computer Science 2026-04-16 Fatih Dinc , Ege Cirakman , Bariscan Kurtkaya , Mert Yuksekgonul , Yiqi Jiang , Mark J. Schnitzer , Hidenori Tanaka

We examine the pre-training dynamics of language models, focusing on their ability to copy text from preceding context--a fundamental skill for various LLM applications, including in-context learning (ICL) and retrieval-augmented generation…

Computation and Language · Computer Science 2025-02-07 Ang Lv , Ruobing Xie , Xingwu Sun , Zhanhui Kang , Rui Yan

The study of Deep Network (DN) training dynamics has largely focused on the evolution of the loss function, evaluated on or around train and test set data points. In fact, many DN phenomenon were first introduced in literature with that…

Machine Learning · Computer Science 2023-10-23 Ahmed Imtiaz Humayun , Randall Balestriero , Richard Baraniuk

In the era of proliferation of large language and image generation models, the phenomenon of "model collapse" refers to the situation whereby as a model is trained recursively on data generated from previous generations of itself over time,…

Machine Learning · Computer Science 2024-05-02 Elvis Dohmatob , Yunzhen Feng , Julia Kempe

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 lens of Singular…

Machine Learning · Statistics 2026-05-08 Ben Cullen , Sergio Estan-Ruiz , Riya Danait , Jiayi Li

Recently it has been observed that neural networks exhibit Neural Collapse (NC) during the final stage of training for the classification problem. We empirically show that multivariate regression, as employed in imitation learning and other…

Machine Learning · Computer Science 2025-09-30 George Andriopoulos , Zixuan Dong , Li Guo , Zifan Zhao , Keith Ross

The learning dynamics of deep neural networks are not well understood. The information bottleneck (IB) theory proclaimed separate fitting and compression phases. But they have since been heavily debated. We comprehensively analyze the…

Machine Learning · Computer Science 2023-12-15 Johannes Schneider , Mohit Prabhushankar

This paper explores the connection between two recently identified phenomena in deep learning: plasticity loss and neural collapse. We analyze their correlation in different scenarios, revealing a significant association during the initial…

Machine Learning · Computer Science 2024-04-04 Guglielmo Bonifazi , Iason Chalas , Gian Hess , Jakub Łucki

Among many mysteries behind the success of deep networks lies the exceptional discriminative power of their learned representations as manifested by the intriguing Neural Collapse (NC) phenomenon, where simple feature structures emerge at…

Machine Learning · Computer Science 2025-10-27 Hancheng Min , Zhihui Zhu , René Vidal

We design and analyze a new paradigm for building supervised learning networks, driven only by local optimization rules without relying on a global error function. Traditional neural networks with a fixed topology are made up of identical…

Adaptation and Self-Organizing Systems · Physics 2024-10-04 S. Barland , L. Gil

Grokking in transformers trained on algorithmic tasks is characterized by a long delay between training-set fit and abrupt generalization, but the source of that delay remains poorly understood. In encoder-decoder arithmetic models, we…

Machine Learning · Computer Science 2026-04-16 Laura Gomezjurado Gonzalez

Although overparameterized models have achieved remarkable practical success, their theoretical properties, particularly their generalization behavior, remain incompletely understood. The well known double descents phenomenon suggests that…

Machine Learning · Statistics 2026-01-06 Haoran Zhan , Yingcun Xia

Deep neural networks exhibit periodic loss spikes during unregularized long-term training, a phenomenon known as the "Slingshot Mechanism." Existing work usually attributes this to intrinsic optimization dynamics, but its triggering…

Machine Learning · Computer Science 2026-05-27 Liu Hanqing , Jianjun Cao , Yuanze Li , Zijian Zhou

Since the proposal of the graph neural network (GNN) by Gori et al. (2005) and Scarselli et al. (2008), one of the major problems in training GNNs was their struggle to propagate information between distant nodes in the graph. We propose a…

Machine Learning · Computer Science 2021-03-10 Uri Alon , Eran Yahav

The Information Bottleneck theory provides a theoretical and computational framework for finding approximate minimum sufficient statistics. Analysis of the Stochastic Gradient Descent (SGD) training of a neural network on a toy problem has…

Machine Learning · Computer Science 2022-12-27 Cipta Herwana , Abhishek Kadian

Although deep neural networks achieve tremendous success on various classification tasks, the generalization ability drops sheer when training datasets exhibit long-tailed distributions. One of the reasons is that the learned…

Machine Learning · Computer Science 2023-02-27 Xuantong Liu , Jianfeng Zhang , Tianyang Hu , He Cao , Lujia Pan , Yuan Yao

The grokking phenomenon as reported by Power et al. ( arXiv:2201.02177 ) refers to a regime where a long period of overfitting is followed by a seemingly sudden transition to perfect generalization. In this paper, we attempt to reveal the…

Machine Learning · Computer Science 2022-06-14 Vimal Thilak , Etai Littwin , Shuangfei Zhai , Omid Saremi , Roni Paiss , Joshua Susskind
‹ Prev 1 4 5 6 7 8 10 Next ›