English
Related papers

Related papers: The Underlying Scaling Laws and Universal Statisti…

200 papers

This work analyzes singular-value spectra of weight matrices in pretrained transformer models to understand how information is stored at both ends of the spectrum. Using Random Matrix Theory (RMT) as a zero information hypothesis, we…

Machine Learning · Computer Science 2025-11-07 Max Staats , Matthias Thamm , Bernd Rosenow

We analyze statistical properties of the complex system with conditions which manifests through specific constraints on the column/row sum of the matrix elements. The presence of additional constraints besides symmetry leads to new…

Statistical Mechanics · Physics 2015-10-28 Pragya Shukla , Suchetana Sadhukhan

It recently has been found that methods of the statistical theories of spectra can be a useful tool in the analysis of spectra far from levels of Hamiltonian systems. Several examples originate from areas, such as quantitative linguistics…

Statistical Mechanics · Physics 2020-05-26 Rongrong Xie , Weibing Deng , Mauricio P. Pato

Scale-free power law structure describes complex networks derived from a wide range of real world processes. The extensive literature focuses almost exclusively on networks with power law exponent strictly larger than 2, which can be…

Social and Information Networks · Computer Science 2015-09-29 Harry Crane , Walter Dempsey

The population loss of trained deep neural networks often follows precise power-law scaling relations with either the size of the training dataset or the number of parameters in the network. We propose a theory that explains the origins of…

Machine Learning · Computer Science 2024-06-28 Yasaman Bahri , Ethan Dyer , Jared Kaplan , Jaehoon Lee , Utkarsh Sharma

Through simple analytical calculations and numerical simulations, we demonstrate the generic existence of a self-organized macroscopic state in any large multivariate system possessing non-vanishing average correlations between a finite…

Statistical Mechanics · Physics 2015-06-24 Y. Malevergne , D. Sornette

Scaling laws, a defining feature of deep learning, reveal a striking power-law improvement in model performance with increasing dataset and model size. Yet, their mathematical origins, especially the scaling exponent, have remained elusive.…

Machine Learning · Computer Science 2026-03-24 Yuda Bi , Vince D Calhoun

Modern Machine Learning (ML) and Deep Neural Networks (DNNs) often operate on high-dimensional data and rely on overparameterized models, where classical low-dimensional intuitions break down. In particular, the proportional regime where…

Machine Learning · Statistics 2026-04-17 Zhenyu Liao , Michael W. Mahoney

Random matrix theory (RMT) is based on two assumptions: (1) matrix-element independence, and (2) base invariance. Most of the proposed generalizations keep the first assumption and violate the second. Recently, several authors presented…

Statistical Mechanics · Physics 2009-07-14 A. Y. Abul-Magd

Empirically, large-scale deep learning models often satisfy a neural scaling law: the test error of the trained model improves polynomially as the model size and data size grow. However, conventional wisdom suggests the test error consists…

Machine Learning · Computer Science 2025-06-11 Licong Lin , Jingfeng Wu , Sham M. Kakade , Peter L. Bartlett , Jason D. Lee

We consider settings where the observations are drawn from a zero-mean multivariate (real or complex) normal distribution with the population covariance matrix having eigenvalues of arbitrary multiplicity. We assume that the eigenvectors of…

Statistics Theory · Mathematics 2009-01-22 N. Raj Rao , James A. Mingo , Roland Speicher , Alan Edelman

Interpreting the representation and generalization powers has been a long-standing issue in the field of machine learning (ML) and artificial intelligence. This work contributes to uncovering the emergence of universal scaling laws in…

Quantum Physics · Physics 2025-03-26 Sheng-Chen Bai , Shi-Ju Ran

Random contractions (sub-unitary random matrices) appear naturally when considering quantized chaotic maps within a general theory of open linear stationary systems with discrete time. We analyze statistical properties of complex…

Chaotic Dynamics · Physics 2009-10-31 Yan V. Fyodorov , H. -J. Sommmers

We present a random-matrix realization of a two-dimensional percolation model with the occupation probability $p$. We find that the behavior of the model is governed by the two first extreme eigenvalues. While the second extreme eigenvalue…

Statistical Mechanics · Physics 2022-02-23 Sina Saber , Abbas Ali Saberi

From benign overfitting in overparameterized models to rich power-law scalings in performance, simple ridge regression displays surprising behaviors sometimes thought to be limited to deep neural networks. This balance of phenomenological…

Machine Learning · Statistics 2026-05-08 Alexander Atanasov , Jacob A. Zavatone-Veth , Cengiz Pehlevan

Scattering of electromagnetic waves in billiard-like systems has become a standard experimental tool of studying properties associated with Quantum Chaos. Random Matrix Theory (RMT) describing statistics of eigenfrequencies and associated…

Disordered Systems and Neural Networks · Physics 2021-05-11 Yan V Fyodorov

Random feature maps are ubiquitous in modern statistical machine learning, where they generalize random projections by means of powerful, yet often difficult to analyze nonlinear operators. In this paper, we leverage the "concentration"…

Machine Learning · Statistics 2021-03-18 Zhenyu Liao , Romain Couillet

The intrinsic dynamical complexity of classically chaotic systems enforces a universal description of the transport properties of their wave-mechanical analogues. These universal rules have been established within the framework of linear…

Optics · Physics 2023-01-02 Cheng-Zhen Wang , Rodion Kononchuk , Ulrich Kuhl , Tsampikos Kottos

Complex, multivariable systems are often analyzed by grouping their constituent units into components, sometimes referred to as latent features, which afford physical or biological interpretation. However, a priori many different types of…

Disordered Systems and Neural Networks · Physics 2026-05-01 Philipp Fleig , Ilya Nemenman

Random matrix theory has become a cornerstone in modern statistics and data science, providing fundamental tools for understanding high-dimensional covariance structures. Within this framework, the Wishart matrix plays a central role in…

Statistics Theory · Mathematics 2025-11-26 Fengcheng Liu