English
Related papers

Related papers: Anomalous Fluctuations in Autoregressive Models wi…

200 papers

Students have a limited time to study and are typically ineffective at allocating study time. Machine-directed study strategies that identify which items need reinforcement and dictate the spacing of repetition have been shown to help…

Computers and Society · Computer Science 2018-03-02 Shane Mooney , Karen Sun , Eric Bomgardner

Self-similar dynamical processes are characterized by a growing length scale $\xi$ which increases with time as $\xi \sim t^{1/z}$, where z is the dynamical exponent. The best known example is a simple random walk with z=2. Usually such…

Statistical Mechanics · Physics 2016-01-18 Lukas Kades , Manuel Schrauth , Maximilian Schneider , Haye Hinrichsen

Autoregressive Transformers are strong language models but incur O(T) complexity during per-token generation due to the self-attention mechanism. Recent work proposes kernel-based methods to approximate causal self-attention by replacing it…

Machine Learning · Computer Science 2022-10-11 Huanru Henry Mao

Recent empirical studies have demonstrated long-memory in the signs of orders to buy or sell in financial markets [2, 19]. We show how this can be caused by delays in market clearing. Under the common practice of order splitting, large…

Other Condensed Matter · Physics 2009-11-10 F. Lillo , Szabolcs Mike , J. Doyne Farmer

Let M be a compact Riemannian manifold with smooth boundary. We obtain the exact long time asymptotic behaviour of the heat kernel on abelian coverings of M with mixed Dirichlet and Neumann boundary conditions. As an application, we study…

Analysis of PDEs · Mathematics 2018-04-05 Xi Geng , Gautam Iyer

The role of memory time fluctuations for instabilities in random media is considered. It is shown that fluctuations can result in infinitely fast growth of statistical moments. The effect is demonstrated in the framework of light…

Plasma Physics · Physics 2025-01-13 S. Pavlenko , E. Illarionov , D. Sokoloff

We study the time correlation function of a density field in two-dimensional driven diffusive systems within the framework of fluctuating hydrodynamics. It is found that the time correlation exhibits power-law behavior in an intermediate…

Statistical Mechanics · Physics 2009-03-02 Takenobu Nakamura , Michio Otsuki , Shin-ichi Sasa

Consider first a memoryless population model described by the usual branching process with a given mean reproduction matrix on a finite space of types. Motivated by the consequences of atavism in Evolutionary Biology, we are interested in a…

Probability · Mathematics 2025-01-03 Jean Bertoin

There is a recent trend in machine learning to increase model quality by growing models to sizes previously thought to be unreasonable. Recent work has shown that autoregressive generative models with cross-entropy objective functions…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-18 Jasha Droppo , Oguz Elibol

We propose a simple mechanism by which scaling laws emerge from feature learning in multi-layer networks. We study a high-dimensional hierarchical target that is a globally high-degree function, but that can be represented by a combination…

Machine Learning · Statistics 2026-05-15 Arie Wortsman-Zurich , Hugo Tabanelli , Yatin Dandi , Florent Krzakala , Bruno Loureiro

Many natural phenomena can be described by power-laws. A closer look at various experimental data reveals more or less significant deviations from a 1/f spectrum. We exemplify such cases with phenomena offered by molecular biology, cell…

Biological Physics · Physics 2008-08-08 Vasile V Morariu , Calin Vamos , Alexadru Pop , Stefan M Soltuz , Luiza Buimaga-Iarinca , Oana Zainea

Based on the Langevin description of the Continuous Time Random Walk (CTRW), we consider a generalization of CTRW in which the waiting times between the subsequent jumps are correlated. We discuss the cases of exponential and slowly…

Statistical Mechanics · Physics 2015-05-13 A. V. Chechkin , M. Hofmann , I. M. Sokolov

We study by theoretical analysis and by direct numerical simulation the dynamics of a wide class of asynchronous stochastic systems composed of many autocatalytic degrees of freedom. We describe the generic emergence of truncated power laws…

Statistical Mechanics · Physics 2009-10-31 Zhi-Feng Huang , Sorin Solomon

We propose a mechanism to produce fluctuations in the viscosity parameter ($\alpha$) in differetially rotating discs. We carried out a nonlinear analysis of a general accretion flow, where any perturbation on the background $\alpha$ was…

High Energy Astrophysical Phenomena · Physics 2015-06-17 S. R. Rajesh , Nishant K. Singh

We characterize the power-law asymptotics of learning curves for Gaussian process regression (GPR) under the assumption that the eigenspectrum of the prior and the eigenexpansion coefficients of the target function follow a power law. Under…

Machine Learning · Computer Science 2021-11-30 Hui Jin , Pradeep Kr. Banerjee , Guido Montúfar

Large language models with a huge number of parameters, when trained on near internet-sized number of tokens, have been empirically shown to obey neural scaling laws: specifically, their performance behaves predictably as a power law in…

Machine Learning · Computer Science 2022-11-01 Alexander Maloney , Daniel A. Roberts , James Sully

Training large models is both resource-intensive and time-consuming, making it crucial to understand the quantitative relationship between model performance and hyperparameters. In this paper, we present an empirical law that describes how…

Machine Learning · Computer Science 2025-03-18 Kairong Luo , Haodong Wen , Shengding Hu , Zhenbo Sun , Zhiyuan Liu , Maosong Sun , Kaifeng Lyu , Wenguang Chen

We consider a dynamical system which has a stable attractor and which is perturbed by an additive noise. Under some quite typical conditions, the fluctuations from the attractor are intermittent and have a probability distribution with…

Chaotic Dynamics · Physics 2015-02-23 Michael Wilkinson , Robin Guichardaz , Marc Pradas , Alain Pumir

We study the motion of a one-dimensional particle which reverses its direction of acceleration stochastically. We focus on two contrasting scenarios, where the waiting-times between two consecutive acceleration reversals are drawn from (i)…

Statistical Mechanics · Physics 2023-08-22 Ion Santra , Durgesh Ajgaonkar , Urna Basu

An analytical expression is derived for the transition path time distribution for a one-dimensional particle crossing of a parabolic barrier. Two cases are analyzed: (i) A non-Markovian process described by a generalized Langevin equation…

Statistical Mechanics · Physics 2018-06-29 E. Carlon , H. Orland , T. Sakaue , C. Vanderzande
‹ Prev 1 4 5 6 7 8 10 Next ›