English
Related papers

Related papers: Intrinsic Complexity And Scaling Laws: From Random…

200 papers

We consider a class of rotationally invariant unitary random matrix ensembles where the eigenvalue density falls off as an inverse power law. Under a new scaling appropriate for such power law densities (different from the scaling required…

Statistical Mechanics · Physics 2009-11-13 K. A. Muttalib , Mourad E. H. Ismail

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

In discrete convex analysis, the scaling and proximity properties for the class of L$^\natural$-convex functions were established more than a decade ago and have been used to design efficient minimization algorithms. For the larger class of…

Combinatorics · Mathematics 2017-12-13 Satoko Moriguchi , Kazuo Murota , Akihisa Tamura , Fabio Tardella

The family of visibility algorithms were recently introduced as mappings between time series and graphs. Here we extend this method to characterize spatially extended data structures by mapping scalar fields of arbitrary dimension into…

Data Analysis, Statistics and Probability · Physics 2017-09-13 Lucas Lacasa , Jacopo Iacovacci

Entanglement entropy for nonlocal field theories displays a universal ``volume law" scaling \cite{Barbon:2008ut, Karczmarek:2013xxa, Shiba:2013jja, Pang:2014tpa} as opposed to the ``area law" scaling for local field theories. The aim of…

High Energy Physics - Theory · Physics 2026-01-28 Mohan sai Balusu , Gaurav Katoch , Sanhita Parihar , Shubho R. Roy

The first main result of this paper is that the law of the (rescaled) two-dimensional uniform spanning tree is tight in a space whose elements are measured, rooted real trees continuously embedded into Euclidean space. Various properties of…

Probability · Mathematics 2017-07-04 M. T. Barlow , D. A. Croydon , T. Kumagai

Quantum systems are the ultimate touchstone for the production of random sequences of numbers. Spatially spread entangled systems allow the generation of identical random sequences in remote locations. The impossibility of observing a…

Quantum Physics · Physics 2018-10-31 Marcelo G. Kovalsky , Alejandro A. Hnilo , Mónica B. Agüero

Random matrix theory is finding an increasing number of applications in the context of information theory and communication systems, especially in studying the properties of complex networks. Such properties include short-term and long-term…

Mathematical Physics · Physics 2015-01-13 Sherif M. Abuelenin , Adel Y. Abul-Magd

Many physical systems share the property of scale invariance. Most of them show ordinary power-law scaling, where quantities can be expressed as a leading power law times a scaling function which depends on scaling-invariant ratios of the…

Statistical Mechanics · Physics 2009-11-07 Lionel Sittler , Haye Hinrichsen

As an alternative to the well-known methods of "chaining" and "bracketing" that have been developed in the study of random fields, a new method, which is based on a {\em stochastic maximal inequality} derived by using the formula for…

Probability · Mathematics 2017-08-16 Yoichi Nishiyama

Intrinsic computation refers to how dynamical systems store, structure, and transform historical and spatial information. By graphing a measure of structural complexity against a measure of randomness, complexity-entropy diagrams display…

Chaotic Dynamics · Physics 2009-11-13 David P. Feldman , Carl S. McTague , James P. Crutchfield

Random heteropolymers are a minimal description of biopolymers and can provide a theoretical framework to the investigate the formation of loops in biophysical experiments. A two--state model provides a consistent and robust way to study…

Quantitative Methods · Quantitative Biology 2016-09-28 Y. Zhan , L. Giorgetti , G. Tiana

How do neural language models acquire a language's structure when trained for next-token prediction? We address this question by deriving theoretical scaling laws for neural network performance on synthetic datasets generated by the Random…

Machine Learning · Computer Science 2025-05-13 Francesco Cagnetta , Alessandro Favero , Antonio Sclocchi , Matthieu Wyart

We prove a local law in the bulk of the spectrum for random Gram matrices $XX^*$, a generalization of sample covariance matrices, where $X$ is a large matrix with independent, centered entries with arbitrary variances. The limiting…

Probability · Mathematics 2017-03-13 Johannes Alt , László Erdős , Torben Krüger

Arranging the bits of a random string or real into k columns of a two-dimensional array or higher dimensional structure is typically accompanied with loss in the Kolmogorov complexity of the columns, which depends on k. We quantify and…

Logic · Mathematics 2026-02-19 George Barmpalias , Xiaoyan Zhang

Scaling laws have played a major role in the modern AI revolution, providing practitioners predictive power over how the model performance will improve with increasing data, compute, and number of model parameters. This has spurred an…

Machine Learning · Computer Science 2026-01-16 Maissam Barkeshli , Alberto Alfarano , Andrey Gromov

A novel random field model or the reconstruction of turbulent velocity fluctuations from inhomogeneous characteristic flow quantities in terms of stochastic Fourier-type integrals has recently been introduced and analyzed by the authors.…

Fluid Dynamics · Physics 2026-04-30 Markus Antoni , Quinten Kürpick , Felix Lindner , Nicole Marheineke , Raimund Wegener

We propose an alternative method to generate samples of a spatially correlated random field with applications to large-scale problems for forward propagation of uncertainty. A classical approach for generating these samples is the…

Numerical Analysis · Mathematics 2017-03-27 Sarah Osborn , Panayot Vassilevski , Umberto Villa

Many random processes can be simulated as the output of a deterministic model accepting random inputs. Such a model usually describes a complex mathematical or physical stochastic system and the randomness is introduced in the input…

Machine Learning · Statistics 2012-11-21 A. Gokcen Mahmutoglu , Alper T. Erdogan , Alper Demir

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