English
Related papers

Related papers: Dimensional Criticality at Grokking Across MLPs an…

200 papers

Why does a Transformer that has memorized its training set wait thousands of steps before it generalizes? Existing accounts locate this delay in norm minimization, feature emergence, or the late discovery of sparse subnetworks. These…

Machine Learning · Computer Science 2026-05-18 Kai Hidajat , Solden Stoll , Joseph An

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, 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…

Machine Learning · Computer Science 2025-04-15 Zihan Gu , Ruoyu Chen , Hua Zhang , Yue Hu , Xiaochun Cao

A fast method is presented for simulating the dielectric-breakdown model using iterated conformal mappings. Numerical results for the dimension and for corrections to scaling are in good agreement with the recent RG prediction of an upper…

Soft Condensed Matter · Physics 2009-11-07 M. B. Hastings

Out-Of-Distribution (OOD) generalization has gained increasing attentions for machine learning on graphs, as graph neural networks (GNNs) often exhibit performance degradation under distribution shifts. Existing graph OOD methods tend to…

Machine Learning · Computer Science 2025-05-12 Henan Sun , Xunkai Li , Lei Zhu , Junyi Han , Guang Zeng , Ronghua Li , Guoren Wang

Grokking is proposed and widely studied as an intricate phenomenon in which generalization is achieved after a long-lasting period of overfitting. In this work, we propose NeuralGrok, a novel gradient-based approach that learns an optimal…

Machine Learning · Computer Science 2025-04-28 Xinyu Zhou , Simin Fan , Martin Jaggi , Jie Fu

While deep learning demonstrates its strong ability to handle independent and identically distributed (IID) data, it often suffers from out-of-distribution (OoD) generalization, where the test data come from another distribution (w.r.t. the…

Machine Learning · Computer Science 2020-12-18 Haoyue Bai , Rui Sun , Lanqing Hong , Fengwei Zhou , Nanyang Ye , Han-Jia Ye , S. -H. Gary Chan , Zhenguo Li

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…

Machine Learning · Computer Science 2024-12-17 Hu Qiye , Zhou Hao , Yu RuoXi

We present a theoretical explanation of the ``grokking'' phenomenon, where a model generalizes long after overfitting,for the originally-studied problem of modular addition. First, we show that early in gradient descent, when the ``kernel…

Machine Learning · Computer Science 2024-07-18 Mohamad Amin Mohamadi , Zhiyuan Li , Lei Wu , Danica J. Sutherland

Our study connects the physics of disordered integer-dimensional systems and regular self-similar objects by studying spectral properties of fractal agglomerates with tunable dimension. The latter is controlled by parameter $\alpha$ of the…

Disordered Systems and Neural Networks · Physics 2026-04-10 Oleg I. Utesov , Alexei Andreanov , Tomasz Bednarek , Alexandra Siklitskaya , Sergei V. Koniakhin

Deep neural networks (DNNs) exhibit crackling-like avalanches whose origin lacks a mechanistic explanation. Here, I derive a stochastic theory of deep information propagation (DIP) by incorporating Central Limit Theorem (CLT)-level…

Disordered Systems and Neural Networks · Physics 2025-12-02 Arsham Ghavasieh

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

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…

Machine Learning · Statistics 2024-02-06 Noam Levi , Alon Beck , Yohai Bar-Sinai

The vulcanization transition - the crosslink-density-controlled equilibrium phase transition from the liquid to the amorphous solid state - is explored analytically from a renormalization group perspective. The analysis centers on a minimal…

Disordered Systems and Neural Networks · Physics 2009-10-31 Weiqun Peng , Paul M. Goldbart

We study the dynamical large deviations (LD) of a class of one-dimensional kinetically constrained models whose (tilted) generators can be mapped into themselves via duality transformations. We consider four representative models in detail:…

Statistical Mechanics · Physics 2025-04-03 Konstantinos Sfairopoulos , Luke Causer , Juan P. Garrahan

Traditional machine learning methods heavily rely on the independent and identically distribution assumption, which imposes limitations when the test distribution deviates from the training distribution. To address this crucial issue,…

Machine Learning · Computer Science 2024-03-26 Qin Tian , Wenjun Wang , Chen Zhao , Minglai Shao , Wang Zhang , Dong Li

The coil-globule transition of an isolated polymer has been well established to be a second-order phase transition described by a standard tricritical O(0) field theory. We provide compelling evidence from Monte Carlo simulations in four…

Statistical Mechanics · Physics 2009-10-31 A. L. Owczarek , T. Prellberg

Disorder is ubiquitous in solid-state systems, and its crucial influence on transport properties was revealed by the discovery of Anderson localization. Generally speaking, all bulk states will be exponentially localized in the strong…

Disordered Systems and Neural Networks · Physics 2023-11-01 Tong Wang , Zhiming Pan , Keith Slevin , Tomi Ohtsuki

Transition points mark qualitative changes in the macroscopic properties of large complex systems. Explosive transitions, exhibiting properties of both continuous and discontinuous phase transitions, have recently been uncovered in network…

Physics and Society · Physics 2021-06-01 Nora Molkenthin , Malte Schröder , Marc Timme

We perform large-scale numerical simulations to investigate the critical behavior of $k$-core percolation in two dimensions with an extended interaction range $r$. By systematically varying both the core index $k$ and the interaction range…

Statistical Mechanics · Physics 2026-05-26 Qiyuan Shi , Ming Li , Youjin Deng