English
Related papers

Related papers: The Complexity Dynamics of Grokking

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

We present a comprehensive analysis of how two-layer neural networks learn features to solve the modular addition task. Our work provides a full mechanistic interpretation of the learned model and a theoretical explanation of its training…

Machine Learning · Computer Science 2026-02-20 Jianliang He , Leda Wang , Siyu Chen , Zhuoran Yang

In-context learning enables transformers to adapt to new tasks from a few examples at inference time, while grokking highlights that this generalization can emerge abruptly only after prolonged training. We study task generalization and…

Machine Learning · Statistics 2026-04-15 Abdessamed Qchohi , Simone Rossi

Grokking, the sudden generalization that occurs after prolonged overfitting, is a surprising phenomenon challenging our understanding of deep learning. Although significant progress has been made in understanding grokking, the reasons…

Machine Learning · Computer Science 2025-05-20 Lucas Prieto , Melih Barsbey , Pedro A. M. Mediano , Tolga Birdal

Generalization is one of the fundamental issues in machine learning. However, traditional techniques like uniform convergence may be unable to explain generalization under overparameterization. As alternative approaches, techniques based on…

Machine Learning · Computer Science 2022-03-22 Jiaye Teng , Jianhao Ma , Yang Yuan

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

We propose a new approach to the problem of neural network expressivity, which seeks to characterize how structural properties of a neural network family affect the functions it is able to compute. Our approach is based on an interrelated…

Machine Learning · Statistics 2017-06-20 Maithra Raghu , Ben Poole , Jon Kleinberg , Surya Ganguli , 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

Classical rate-distortion theory requires knowledge of an elusive source distribution. Instead, we analyze rate-distortion properties of individual objects using the recently developed algorithmic rate-distortion theory. The latter is based…

Information Theory · Computer Science 2007-07-16 Steven de Rooij , Paul Vitanyi

Understanding generalization in modern machine learning settings has been one of the major challenges in statistical learning theory. In this context, recent years have witnessed the development of various generalization bounds suggesting…

Machine Learning · Statistics 2022-07-01 Milad Sefidgaran , Amin Gohari , Gaël Richard , Umut Şimşekli

Deep neural networks generalize well on unseen data though the number of parameters often far exceeds the number of training examples. Recently proposed complexity measures have provided insights to understanding the generalizability in…

Machine Learning · Computer Science 2020-05-12 Jingling Li , Yanchao Sun , Jiahao Su , Taiji Suzuki , Furong Huang

Training Neural Networks (NNs) without overfitting is difficult; detecting that overfitting is difficult as well. We present a novel Random Matrix Theory method that detects the onset of overfitting in deep learning models without access to…

Machine Learning · Computer Science 2026-05-15 Hari K. Prakash , Charles H Martin

Existing accounts of grokking explain the phenomena in terms of mechanistic frameworks such as circuit efficiency or lazy-to-rich transitions. However, despite a known dependence between grokking and model size, how model capacity shapes…

Machine Learning · Computer Science 2026-05-12 Yiding Song , Hanming Ye

Spectral bias, the tendency of neural networks to learn low frequencies first, can be both a blessing and a curse. While it enhances the generalization capabilities by suppressing high-frequency noise, it can be a limitation in scientific…

Machine Learning · Computer Science 2026-05-08 Shuai Jiang , Alexey Voronin , Eric Cyr , Ben Southworth

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

In recent years, great progress has been made in a variety of application domains thanks to the development of increasingly deeper neural networks. Unfortunately, the huge number of units of these networks makes them expensive both…

Computer Vision and Pattern Recognition · Computer Science 2018-10-12 Jose M. Alvarez , Mathieu Salzmann

Despite their empirical success, how diffusion models generalize remains poorly understood from a mechanistic perspective. We demonstrate that diffusion models trained with flow-matching objectives exhibit grokking--delayed generalization…

Machine Learning · Computer Science 2026-04-21 Joon Hyeok Kim , Yong-Hyun Park , Mattis Dalsætra Østby , Jiatao Gu

We study networks of noisy phase oscillators whose nodes are characterized by a random degree counting the number of its connections. Both these degrees and the natural frequencies of the oscillators are distributed according to a given…

Chaotic Dynamics · Physics 2012-05-15 Bernard Sonnenschein , Lutz Schimansky-Geier

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

Regularization is typically understood as improving generalization by altering the landscape of local extrema to which the model eventually converges. Deep neural networks (DNNs), however, challenge this view: We show that removing…

Machine Learning · Computer Science 2019-06-03 Aditya Golatkar , Alessandro Achille , Stefano Soatto
‹ Prev 1 3 4 5 6 7 10 Next ›