English
Related papers

Related papers: How to explain grokking

200 papers

We consider the problem of building a continuous stochastic model, i.e. a Langevin or Fokker-Planck equation, through a well-controlled coarse-graining procedure. Such a method usually involves the elimination of the fast degrees of freedom…

Statistical Mechanics · Physics 2019-07-08 Marco Baldovin , Angelo Vulpiani , Andrea Puglisi , Antonio Prados

We analyze some basic issues associated with Generalized Poisson-Kac (GPK) stochastic processes, starting from the extended notion of the Markovian condition. The extended Markovian nature of GPK processes is established, and the…

Statistical Mechanics · Physics 2017-03-08 Massimiliano Giona , Antonio Brasiello , Silvestro Crescitelli

We investigate stochastic processes that generalize geometric Brownian motion, focusing on cases where the standard invariant measure, i.e. the solution of the stationary Fokker-Planck equation does not necessarily exist. We demonstrate…

Statistical Mechanics · Physics 2026-02-18 S. Giordano , R. Blossey

Language provides simple ways of communicating generalizable knowledge to each other (e.g., "Birds fly", "John hikes", "Fire makes smoke"). Though found in every language and emerging early in development, the language of generalization is…

Computation and Language · Computer Science 2018-12-17 Michael Henry Tessler , Noah D. Goodman

A short review of the classical theory of Brownian motion is presented. A new method is proposed for derivation of the Fokker-Planck equations, describing the probability density evolution, from stochastic differential equations. It is also…

Statistical Mechanics · Physics 2011-04-07 Roumen Tsekov

This is a guide to the mathematical theory of Brownian motion and related stochastic processes, with indications of how this theory is related to other branches of mathematics, most notably the classical theory of partial differential…

Probability · Mathematics 2018-02-28 Jim Pitman , Marc Yor

Training dynamics during grokking concentrate along a small number of dominant update directions -- the spectral edge -- which reliably distinguishes grokking from non-grokking regimes. We show that standard mechanistic interpretability…

Machine Learning · Computer Science 2026-04-09 Yongzhong Xu

Physical scenarios that require a relativistic treatment are ubiquitous in nature, ranging from cosmological objects to charge carriers in Dirac materials. Interestingly all of these situations have in common that the systems typically…

Statistical Mechanics · Physics 2020-08-11 P. S. Pal , Sebastian Deffner

The generalised Langevin equation with a retarded friction and a double-well potential is solved. The random force is modelled by a multiplicative noise with long jumps. Probability density distributions converge with time to a distribution…

Statistical Mechanics · Physics 2015-06-16 Tomasz Srokowski

The focus of our study in this paper is on the active dynamics and a fractional generalized Langevin equation with a memory kernel K(t). The Fokker-Planck equation is obtained by deriving it from a second-order differential equation. The…

Statistical Mechanics · Physics 2024-12-17 Yun Jeong Kang , Kyungsik Kim

Recently there has been remarkable progress in the complex Langevin method, which aims at solving the complex action problem by complexifying the dynamical variables in the original path integral. In particular, a new technique called the…

High Energy Physics - Lattice · Physics 2015-12-30 Keitaro Nagata , Jun Nishimura , Shinji Shimasaki

This paper investigates the impact of different optimizers on the grokking phenomenon, where models exhibit delayed generalization. We conducted experiments across seven numerical tasks (primarily modular arithmetic) using a modern…

Machine Learning · Computer Science 2025-04-23 Amund Tveit , Bjørn Remseth , Arve Skogvold

A model has two main aims: predicting the behavior of a physical system and understanding its nature, that is how it works, at some desired level of abstraction. A promising recent approach to model building consists in deriving a…

Statistical Mechanics · Physics 2019-02-26 Marco Baldovin , Andrea Puglisi , Angelo Vulpiani

Stochastic inflation rests on the separate-universe approximation, i.e. the ability to describe long-wavelength fluctuations in an inflating universe as homogeneous perturbations of its background dynamics. Although this approximation is…

Cosmology and Nongalactic Astrophysics · Physics 2025-12-16 Vadim Briaud , Ryodai Kawaguchi , Vincent Vennin

Nonergodic Brownian motion is elucidated within the framework of the generalized Langevin equation. For thermal noise yielding either a vanishing or a divergent zero-frequency friction strength, the non-Markovian Browninan dynamics exhibits…

Statistical Mechanics · Physics 2007-05-23 Jing-Dong Bao , Yi-Zhong Zhuo , Fernando A. Oliveira , Peter Hänggi

The fluctuation-dissipation theorem is a central result in statistical mechanics and is usually formulated for systems described by diffusion processes. In this paper, we propose a generalization for a wider class of stochastic processes,…

Statistical Mechanics · Physics 2018-09-20 Alberto Montefusco , Mark A. Peletier , Hans Christian Öttinger

We present a numerical method to produce stochastic dynamics according to the generalized Langevin equation with a non-stationary memory kernel. This type of dynamics occurs when a microscopic system with an explicitly time-dependent…

Statistical Mechanics · Physics 2022-11-30 Christoph Widder , Fabian Glatzel , Tanja Schilling

We design and analyze a new paradigm for building supervised learning networks, driven only by local optimization rules without relying on a global error function. Traditional neural networks with a fixed topology are made up of identical…

Adaptation and Self-Organizing Systems · Physics 2024-10-04 S. Barland , L. Gil

The coarse-graining approach to deriving the quantum Markovian master equation is revisited, with close attention given to the underlying approximations. It is further argued that the time interval over which the coarse-graining is…

Quantum Physics · Physics 2017-12-05 J D Cresser , C Facer

A major challenge in reinforcement learning is to determine which state-action pairs are responsible for future rewards that are delayed. Reward redistribution serves as a solution to re-assign credits for each time step from observed…

Machine Learning · Computer Science 2023-11-14 Yudi Zhang , Yali Du , Biwei Huang , Ziyan Wang , Jun Wang , Meng Fang , Mykola Pechenizkiy
‹ Prev 1 4 5 6 7 8 10 Next ›