English
Related papers

Related papers: Grokking as Compression: A Nonlinear Complexity Pe…

200 papers

Grokking-delayed generalization that emerges well after a model has fit the training data-has been linked to robustness and representation quality. We ask whether this training regime also helps with machine unlearning, i.e., removing the…

Machine Learning · Computer Science 2025-12-04 Yuanbang Liang , Yang Li

We study grokking, the onset of generalization long after overfitting, in a classical ridge regression setting. We prove end-to-end grokking results for learning over-parameterized linear regression models using gradient descent with weight…

Machine Learning · Computer Science 2026-02-09 Mingyue Xu , Gal Vardi , Itay Safran

Deep learning models have proven enormously successful at using multiple layers of representation to learn relevant features of structured data. Encoding physical symmetries into these models can improve performance on difficult tasks, and…

Machine Learning · Computer Science 2025-10-21 Cassidy Ashworth , Pietro Liò , Francesco Caso

Neural networks trained by gradient descent (GD) have exhibited a number of surprising generalization behaviors. First, they can achieve a perfect fit to noisy training data and still generalize near-optimally, showing that overfitting can…

Machine Learning · Computer Science 2023-10-05 Zhiwei Xu , Yutong Wang , Spencer Frei , Gal Vardi , Wei Hu

Grokking, the sudden transition from memorization to generalization, is characterized by the emergence of low-dimensional representations, yet the mechanism underlying this organization remains elusive. We propose that intrinsic task…

Machine Learning · Computer Science 2026-03-03 Hyeonbin Hwang , Yeachan Park

Grokking - the delayed transition from memorisation to generalisation in neural networks - remains poorly understood. We study this phenomenon through the geometry of learned representations and identify a consistent empirical signature…

Machine Learning · Computer Science 2026-05-13 Truong Xuan Khanh , Truong Quynh Hoa , Luu Duc Trung , Phan Thanh Duc

We propose that learning in deep neural networks proceeds in two phases: a rapid curve fitting phase followed by a slower compression or coarse graining phase. This view is supported by the shared temporal structure of three phenomena:…

High Energy Physics - Theory · Physics 2025-07-28 Robert de Mello Koch , Animik Ghosh

We aim to understand grokking, a phenomenon where models generalize long after overfitting their training set. We present both a microscopic analysis anchored by an effective theory and a macroscopic analysis of phase diagrams describing…

Machine Learning · Computer Science 2022-10-17 Ziming Liu , Ouail Kitouni , Niklas Nolte , Eric J. Michaud , Max Tegmark , Mike Williams

A principled understanding of generalization in deep learning may require unifying disparate observations under a single conceptual framework. Previous work has studied \emph{grokking}, a training dynamic in which a sustained period of…

Machine Learning · Computer Science 2023-03-14 Xander Davies , Lauro Langosco , David Krueger

It is generally well understood that predictive classification and compression are intrinsically related concepts in information theory. Indeed, many deep learning methods are explained as learning a kind of compression, and that better…

Machine Learning · Computer Science 2024-10-22 John Hurwitz , Charles Nicholas , Edward Raff

While Large Language Models (LLMs) excel at factual retrieval, they often struggle with the "curse of two-hop reasoning" in compositional tasks. Recent research suggests that parameter-sharing transformers can bridge this gap by forming a…

Computation and Language · Computer Science 2026-01-15 Kaiyu He , Zhang Mian , Peilin Wu , Xinya Du , Zhiyu Chen

Multiple Kernel Learning is a conventional way to learn the kernel function in kernel-based methods. MKL algorithms enhance the performance of kernel methods. However, these methods have a lower complexity compared to deep learning models…

Machine Learning · Computer Science 2023-05-05 Ahmad Navid Ghanizadeh , Kamaledin Ghiasi-Shirazi , Reza Monsefi , Mohammadreza Qaraei

Grokking typically achieves similar loss to ordinary, "steady", learning. We ask whether these different learning paths - grokking versus ordinary training - lead to fundamental differences in the learned models. To do so we compare the…

In practice it is often found that large over-parameterized neural networks generalize better than their smaller counterparts, an observation that appears to conflict with classical notions of function complexity, which typically favor…

Machine Learning · Statistics 2018-06-20 Roman Novak , Yasaman Bahri , Daniel A. Abolafia , Jeffrey Pennington , Jascha Sohl-Dickstein

We study the grokking phenomenon through the lens of topology. Using persistent homology on point clouds derived from the embedding matrices of a range of models trained on modular arithmetic with varying primes, we identify a clear and…

Machine Learning · Computer Science 2026-05-08 Yifan Tang , Qiquan Wang , Inés García-Redondo , Anthea Monod

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…

Machine Learning · Computer Science 2023-10-23 Neel Nanda , Lawrence Chan , Tom Lieberum , Jess Smith , Jacob Steinhardt

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 grokking can only…

Machine Learning · Computer Science 2023-10-02 Pascal Jr. Tikeng Notsawo , Hattie Zhou , Mohammad Pezeshki , Irina Rish , Guillaume Dumas

The deep linear network (DLN) is a model for implicit regularization in gradient based optimization of overparametrized learning architectures. Training the DLN corresponds to a Riemannian gradient flow, where the Riemannian metric is…

Dynamical Systems · Mathematics 2023-05-12 Nadav Cohen , Govind Menon , Zsolt Veraszto

The large capacity of neural networks enables them to learn complex functions. To avoid overfitting, networks however require a lot of training data that can be expensive and time-consuming to collect. A common practical approach to…

Machine Learning · Computer Science 2020-03-10 Majed El Helou , Frederike Dümbgen , Sabine Süsstrunk

We present a deep neural network to predict structural similarity between 2D layouts by leveraging Graph Matching Networks (GMN). Our network, coined LayoutGMN, learns the layout metric via neural graph matching, using an attention-based…

Computer Vision and Pattern Recognition · Computer Science 2021-04-07 Akshay Gadi Patil , Manyi Li , Matthew Fisher , Manolis Savva , Hao Zhang