English
Related papers

Related papers: Dimensional Criticality at Grokking Across MLPs an…

200 papers

Graph Neural Networks (GNNs) conventionally rely on standard Laplacian or adjacency matrices for structural message passing. In this work, we substitute the traditional Laplacian with a Doubly Stochastic graph Matrix (DSM), derived from the…

Machine Learning · Computer Science 2026-04-17 Zhaobo Hu , Vincent Gauthier , Mehdi Naima

A critical vulnerability of supervised deep learning in high-dimensional tabular domains is "generalization collapse": models form precise decision boundaries around known training distributions but fail catastrophically when encountering…

Machine Learning · Computer Science 2026-03-10 Rajeeb Thapa Chhetri , Saurab Thapa , Avinash Kumar , Zhixiong Chen

A random growth lattice filling model of percolation with touch and stop growth rule is developed and studied numerically on a two dimensional square lattice. Nucleation centers are continuously added one at a time to the empty sites and…

Statistical Mechanics · Physics 2018-06-13 Bappaditya Roy , S. B. Santra

We study the well-known grokking phenomena in neural networks (NNs) using a 3-layer MLP trained on 1 k-sample subset of MNIST, with and without weight decay, and discover a novel third phase -- \emph{anti-grokking} -- that occurs very late…

Machine Learning · Computer Science 2025-06-06 Hari K. Prakash , Charles H. Martin

Graph Neural Network (GNN) has demonstrated extraordinary performance in classifying graph properties. However, due to the selection bias of training and testing data (e.g., training on small graphs and testing on large graphs, or training…

Machine Learning · Computer Science 2023-08-17 Bin Lu , Xiaoying Gan , Ze Zhao , Shiyu Liang , Luoyi Fu , Xinbing Wang , Chenghu Zhou

We study non-interacting systems with a power-law quasiparticle dispersion $\xi_{\bf k}\propto k^\alpha$ and a random short-range-correlated potential. We show that, unlike the case of lower dimensions, for $d>2\alpha$ there exists a…

Mesoscale and Nanoscale Physics · Physics 2015-06-23 S. V. Syzranov , V. Gurarie , L. Radzihovsky

We study dephasing by electron interactions in a small disordered quasi-one dimensional (1D) ring weakly coupled to leads. We use an influence functional for quantum Nyquist noise to describe the crossover for the dephasing time $\Tph (T)$…

Mesoscale and Nanoscale Physics · Physics 2009-12-04 M. Treiber , O. M. Yevtushenko , F. Marquardt , J. von Delft , I. V. Lerner

A numerical study of Anderson transition on random regular graphs (RRG) with diagonal disorder is performed. The problem can be described as a tight-binding model on a lattice with N sites that is locally a tree with constant connectivity.…

Disordered Systems and Neural Networks · Physics 2016-12-28 K. S. Tikhonov , A. D. Mirlin , M. A. Skvortsov

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

Unsupervised anomaly detection of multivariate time series is a challenging task, given the requirements of deriving a compact detection criterion without accessing the anomaly points. The existing methods are mainly based on reconstruction…

Machine Learning · Computer Science 2026-05-26 Qingxiang Liu , Xiaoliang Luo , Chenghao Liu , Sheng Sun , Di Yao , Lvchun Wang , Wei Yu , Yuxuan Liang

Standard Transformers have a fixed computational depth, fundamentally limiting their ability to generalize to tasks requiring variable-depth reasoning, such as multi-hop graph traversal or nested logic. We propose a depth-recurrent…

Machine Learning · Computer Science 2026-03-24 Hung-Hsuan Chen

We investigate the effects of quenched randomness on topological quantum phase transitions in strongly interacting two-dimensional systems. We focus first on transitions driven by the condensation of a subset of fractionalized…

Strongly Correlated Electrons · Physics 2021-03-03 Byungmin Kang , S. A. Parameswaran , Andrew C. Potter , Romain Vasseur , Snir Gazit

Nearly magnetic metals often have layered lattice structures, consisting of coupled planes. In such a situation, physical properties will display, upon decreasing temperature or energy, a dimensional crossover from two-dimensional (2d) to…

Strongly Correlated Electrons · Physics 2009-11-13 Markus Garst , Lars Fritz , Achim Rosch , Matthias Vojta

We implement an efficient strong-disorder renormalization-group (SDRG) procedure to study disordered tight-binding models in any dimension and on the Erdos-Renyi random graphs, which represent an appropriate infinite dimensional limit. Our…

Strongly Correlated Electrons · Physics 2017-08-02 Hossein Javan Mard , Jose A. Hoyos , Eduardo Miranda , Vladimir Dobrosavljevic

Dynamical phase transitions (DPTs) characterize critical changes in system behavior occurring at finite times, providing a lens to study nonequilibrium phenomena beyond conventional equilibrium physics. While extensively studied in quantum…

Physics and Society · Physics 2024-12-10 Jiazhen Liu , Nathaniel M. Aden , Debasish Sarker , Chaoming Song

If a system undergoing phase transitions exhibits some characteristics of both first and second order, it is said to be of 'mixed order' or to display the Thouless effect. Such a transition is present in a simple model of a dynamic social…

Physics and Society · Physics 2019-01-30 R. K. P. Zia , Weibin Zhang , Mohammadmehdi Ezzatabadipour , Kevin E. Bassler

Estimating a fractal dimension from a finite stochastic trajectory is a finite-size scaling problem: the apparent box-counting exponent is shaped by an occupancy crossover between the resolved range of scales and the finite number of…

Statistical Mechanics · Physics 2026-05-28 Bon A. Koo , Edward Ju

The geometry of fracture patterns in a dilute elastic network is explored using molecular dynamics simulation. The network in two dimensions is subjected to a uniform strain which drives the fracture to develop by the growth and coalescence…

Condensed Matter · Physics 2015-06-25 P. Ray , G. Date

Many models and real complex systems possess critical thresholds at which the systems shift from one sate to another. The discovery of the early warnings of the systems in the vicinity of critical point are of great importance to estimate…

Statistical Mechanics · Physics 2017-02-08 Longfeng Zhao , Wei Li , Chunbin Yang , Jihui Han , Zhu Su , Yijiang Zou , Xu Cai

We use high-dimensional bosonization to derive an effective field theory that describes the Pomeranchuck transition in isotropic two-dimensional Fermi liquids. We find that the transition is triggered by the softening of an eigenmode that…

Strongly Correlated Electrons · Physics 2025-11-04 Zhengfei Hu , Jaychandran Padayasi , Oğuz Türker , Kun Yang