English
Related papers

Related papers: Power-law Dynamic arising from machine learning

200 papers

The dynamics of coupled 2D chaotic maps with time-delay on a scalefree-tree is studied, with different types of the collective behaviors already been reported for various values of coupling strength [1]. In this work we focus on the…

Statistical Mechanics · Physics 2008-05-22 Zoran Levnajić

We study a distributed learning process observed in human groups and other social animals. This learning process appears in settings in which each individual in a group is trying to decide over time, in a distributed manner, which option to…

Machine Learning · Computer Science 2017-05-10 L. Elisa Celis , Peter M. Krafft , Nisheeth K. Vishnoi

Recently several authors have proposed stochastic evolutionary models for the growth of complex networks that give rise to power-law distributions. These models are based on the notion of preferential attachment leading to the ``rich get…

Soft Condensed Matter · Physics 2007-05-23 Trevor Fenner , Mark Levene , George Loizou

Long-time behavior of spatial power-law correlation in one-dimensional self-gravitating system is numerically investigated. It is found that the power-law structure persists even after the system is virialized. The structure gradually…

Astrophysics · Physics 2007-05-23 Hiroko Koyama , Tetsuro Konishi

Random walk models, such as the trap model, continuous time random walks, and comb models exhibit weak ergodicity breaking, when the average waiting time is infinite. The open question is: what statistical mechanical theory replaces the…

Statistical Mechanics · Physics 2007-05-23 Golan Bel , Eli Barkai

We consider three distinct discrete-time models of learning and evolution in games: a biological model based on intra-species selective pressure, the dynamics induced by pairwise proportional imitation, and the exponential / multiplicative…

Dynamical Systems · Mathematics 2024-02-27 Fryderyk Falniowski , Panayotis Mertikopoulos

Power-law distributions are widely recognized in complex systems physics as indicative of underlying complexity in interaction networks and critical macroscopic behavior. Previous studies, notably those of Newman and others, have emphasized…

Physics and Society · Physics 2026-05-19 Tommaso Rondini , Gregorio Berselli , Mirko Degli Esposti , Armando Bazzani

We develop the theory of Energy Conserving Descent (ECD) and introduce ECDSep, a gradient-based optimization algorithm able to tackle convex and non-convex optimization problems. The method is based on the novel ECD framework of…

Machine Learning · Computer Science 2023-06-02 G. Bruno De Luca , Alice Gatti , Eva Silverstein

Many biological processes are supported by special molecules, called motor proteins or molecular motors, that transport cellular cargoes along linear protein filaments and can reversibly associate to their tracks. Stimulated by these…

Statistical Mechanics · Physics 2021-11-17 Akriti Jindal , Anatoly B. Kolomeisky , Arvind Kumar Gupta

We study the stationary probability distribution of a system driven by shot noise. We find that, both in the overdamped and underdamped regime, the coordinate distribution displays power-law singularities in its central part. For…

Mesoscale and Nanoscale Physics · Physics 2015-06-12 Akihisa Ichiki , Yukihiro Tadokoro , M. I. Dykman

We consider the extremal values of the stationary distribution of sparse directed random graphs with given degree sequences and their relation to the extremal values of the in-degree sequence. The graphs are generated by the directed…

Probability · Mathematics 2021-04-20 Xing Shi Cai , Pietro Caputo , Guillem Perarnau , Matteo Quattropani

A power law degree distribution is established for a graph evolution model based on the graph class of k-trees. This k-tree-based graph process can be viewed as an idealized model that captures some characteristics of the preferential…

Discrete Mathematics · Computer Science 2008-11-27 Yong Gao

We study the problem of learning the law of linear stochastic partial differential equations (SPDEs) with additive Gaussian forcing from spatiotemporal observations. Most existing deep learning approaches either assume access to the driving…

Machine Learning · Computer Science 2026-02-13 Sebastian Zeng , Andreas Petersson , Wolfgang Bock

We develop an approach to learn an interpretable semi-parametric model of a latent continuous-time stochastic dynamical system, assuming noisy high-dimensional outputs sampled at uneven times. The dynamics are described by a nonlinear…

Machine Learning · Statistics 2019-02-13 Lea Duncker , Gergo Bohner , Julien Boussard , Maneesh Sahani

Following findings by Ormerod and Mounfield, Wright rises the problem whether a power or an exponential law describes the distribution of occurrences of economic recession periods. In order to clarify the controversy a different set of GDP…

Statistical Mechanics · Physics 2009-11-10 Marcel Ausloos , Janusz Miskiewicz , Michele Sanglier

We consider the problem of continuous-time policy evaluation. This consists in learning through observations the value function associated with an uncontrolled continuous-time stochastic dynamic and a reward function. We propose two…

Machine Learning · Computer Science 2023-06-08 Ziad Kobeissi , Francis Bach

This short review describes mathematical techniques for statistical analysis and prediction in dynamical systems. Two problems are discussed, namely (i) the supervised learning problem of forecasting the time evolution of an observable…

Statistics Theory · Mathematics 2020-07-01 Tyrus Berry , Dimitrios Giannakis , John Harlim

We study the ergodic properties of finite-dimensional systems of SDEs driven by non-degenerate additive fractional Brownian motion with arbitrary Hurst parameter $H\in(0,1)$. A general framework is constructed to make precise the notions of…

Probability · Mathematics 2007-05-23 Martin Hairer

Scaling laws describe how learning performance improves with data, compute, or training time, and have become a central theme in modern deep learning. We study this phenomenon in a canonical nonlinear model: phase retrieval with anisotropic…

Machine Learning · Statistics 2025-11-25 Guillaume Braun , Bruno Loureiro , Ha Quang Minh , Masaaki Imaizumi

We develop a theory of ergodicity for a class of random dynamical systems where the driving noise is not white. The two main tools of our analysis are the strong Feller property and topological irreducibility, introduced in this work for a…

Probability · Mathematics 2011-11-09 M. Hairer , A. Ohashi
‹ Prev 1 4 5 6 7 8 10 Next ›