English
Related papers

Related papers: Dimensional Criticality at Grokking Across MLPs an…

200 papers

We discuss basic features of emergent complexity in dynamical systems far from equilibrium by focusing on the network structure of their state space. We start by measuring the distributions of avalanche and transient times in Random Boolean…

Biological Physics · Physics 2009-11-13 Andrew Berdahl , Amer Shreim , Vishal Sood , Joern Davidsen , Maya Paczuski

Graph Neural Networks (GNNs) are susceptible to distribution shifts, creating vulnerability and security issues in critical domains. There is a pressing need to enhance the generalizability of GNNs on out-of-distribution (OOD) test data.…

Machine Learning · Computer Science 2024-10-29 Xiaoxue Han , Huzefa Rangwala , Yue Ning

The dynamical triangulation model of three-dimensional quantum gravity is shown to have a line of transitions in an expanded phase diagram which includes a coupling mu to the order of the vertices. Monte Carlo renormalization group and…

High Energy Physics - Lattice · Physics 2009-10-30 Ray L. Renken , Simon M. Catterall , John B. Kogut

Gradient descent dynamics in complex energy landscapes, i.e. featuring multiple minima, finds application in many different problems, from soft matter to machine learning. Here, we analyze one of the simplest examples, namely that of soft…

Statistical Mechanics · Physics 2022-08-23 Alessandro Manacorda , Francesco Zamponi

One-dimensional non-equilibrium models of particles subjected to a coagulation-diffusion process are important in understanding non-equilibrium dynamics, and fluctuation-dissipation relation. We consider in this paper transport properties…

Statistical Mechanics · Physics 2015-06-18 Jean-Yves Fortin

Deep learning has been demonstrated with tremendous success in recent years. Despite so, its performance in practice often degenerates drastically when encountering out-of-distribution (OoD) data, i.e. training and test data are sampled…

Computer Vision and Pattern Recognition · Computer Science 2024-10-30 Haoyue Bai

Odd diffusion breaks time-reversal symmetry in overdamped systems through transverse probability currents while preserving equilibrium steady states. In this work, we develop a dynamical density functional theory (DDFT) for dense…

Soft Condensed Matter · Physics 2026-02-02 Iman Abdoli , René Wittmann , Hartmut Löwen

Understanding the inductive bias and generalization properties of large overparametrized machine learning models requires to characterize the dynamics of the training algorithm. We study the learning dynamics of large two-layer neural…

Machine Learning · Statistics 2025-10-30 Andrea Montanari , Pierfrancesco Urbani

Non-thermal dynamical critical behavior can arise in isolated quantum systems brought out of equilibirum by a change in time of their parameters. While this phenomenon has been studied in a variety of systems in the case of a sudden quench,…

Statistical Mechanics · Physics 2016-12-21 Anna Maraga , Pietro Smacchia , Alessandro Silva

Deep learning is widely applied in computer-aided pathological diagnosis, which alleviates the pathologist workload and provide timely clinical analysis. However, most models generally require large-scale annotated data for training, which…

Computer Vision and Pattern Recognition · Computer Science 2024-03-12 Zeyu Liu , Tianyi Zhang , Yufang He , Yunlu Feng , Yu Zhao , Guanglei Zhang

We study the scaling limits of stochastic gradient descent (SGD) with constant step-size in the high-dimensional regime. We prove limit theorems for the trajectories of summary statistics (i.e., finite-dimensional functions) of SGD as the…

Machine Learning · Statistics 2023-08-21 Gerard Ben Arous , Reza Gheissari , Aukosh Jagannath

These lecture notes provide an overview of the renormalization group (RG) as a successful framework to understand critical phenomena above the upper critical dimension $d_{\rm uc}$. After an introduction to the scaling picture of continuous…

Statistical Mechanics · Physics 2022-08-17 Bertrand Berche , Tim Ellis , Yurij Holovatch , Ralph Kenna

The superconducting transition is studied within the one-loop renormalization group in fixed dimension $D=3$ and at the critical point. A tricritical behavior is found, and for $\kappa > \kappa_c$, an attractive charged fixed point,…

Condensed Matter · Physics 2009-09-25 Igor F. Herbut , Zlatko Tesanovic

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…

Machine Learning · Statistics 2024-04-12 Tanishq Kumar , Blake Bordelon , Samuel J. Gershman , Cengiz Pehlevan

We perform both analytical and numerical bifurcation analysis of a forest-grassland ecosystem model coupled with human interaction. The model consists of two nonlinear ordinary differential equations incorporating the human perception of…

Numerical Analysis · Mathematics 2023-03-16 Konstantinos Spiliotis , Lucia Russo , Francesco Giannino , Constantinos Siettos

Dynamical and spatial correlations of eigenfunctions as well as energy level correlations in the Anderson model on random regular graphs (RRG) are studied. We consider the critical point of the Anderson transition and the delocalized phase.…

Disordered Systems and Neural Networks · Physics 2019-01-10 K. S. Tikhonov , A. D. Mirlin

Jamming transition is traditionally regarded as a geometric transition governed by static contact networks. Recently, dynamic phase transitions of athermal particles under periodic shearing provide a new lens on this problem, leading to a…

Statistical Mechanics · Physics 2026-04-24 He-Da Wang , Bo Wang , Qun-Li Lei , Yu-Qiang Ma

We investigated the phase transition behavior of a binary spreading process in two dimensions for different particle diffusion strengths ($D$). We found that $N>2$ cluster mean-field approximations must be considered to get consistent…

Statistical Mechanics · Physics 2009-11-07 G. Odor , M. C. Marques , M. A. Santos

We present Link Density (LD) computed from the Recurrence Network (RN) of a time series data as an effective measure that can detect dynamical transitions in a system. We illustrate its use using time series from the standard Rossler system…

Data Analysis, Statistics and Probability · Physics 2024-05-31 Rinku Jacob , R. Misra , K P Harikrishnan , G Ambika

Critical transitions occur in a wide variety of applications including mathematical biology, climate change, human physiology and economics. Therefore it is highly desirable to find early-warning signs. We show that it is possible to…

Dynamical Systems · Mathematics 2015-03-17 Christian Kuehn
‹ Prev 1 4 5 6 7 8 10 Next ›