English
Related papers

Related papers: How to explain grokking

200 papers

We study a class of systems whose dynamics are described by generalized Langevin equations with state-dependent coefficients. We find that in the limit, in which all the characteristic time scales vanish at the same rate, the position…

Mathematical Physics · Physics 2020-12-16 Soon Hoe Lim , Jan Wehr

The crossed product, and consequent transition from von Neumann algebras of type III to II, is recovered from a truncation of more general gravitational dressing constructions, about certain spacetimes. This is done by extending "standard…

High Energy Physics - Theory · Physics 2026-01-12 Steven B. Giddings

Many biological systems can be described by finite Markov models. A general method for simplifying master equations is presented that is based on merging adjacent states. The approach preserves the steady-state probability distribution and…

Biological Physics · Physics 2021-03-01 David Seiferth , Peter Sollich , Stefan Klumpp

Post-hoc interpretability methods typically attribute a model's behavior to its components, data, or training trajectory in isolation. This leads to explanations that lack a unified view and may miss key interactions. While combining…

Machine Learning · Computer Science 2025-10-02 Florian Eichin , Yupei Du , Philipp Mondorf , Maria Matveev , Barbara Plank , Michael A. Hedderich

Exposure bias refers to the train-test discrepancy that seemingly arises when an autoregressive generative model uses only ground-truth contexts at training time but generated ones at test time. We separate the contributions of the model…

Machine Learning · Computer Science 2019-11-11 Florian Schmidt

The complex Langevin method is a promising approach to the complex-action problem based on a fictitious time evolution of complexified dynamical variables under the influence of a Gaussian noise. Although it is known to have a restricted…

High Energy Physics - Lattice · Physics 2017-01-04 Keitaro Nagata , Jun Nishimura , Shinji Shimasaki

We propose a mechanism to explain what occurs when a mixture of grains of different sizes and different shapes (i.e. different repose angles) is poured into a quasi-two-dimensional cell. Specifically, we develop a model that displays…

Statistical Mechanics · Physics 2009-10-31 Hernan A. Makse , Pierre Cizeau , H. Eugene Stanley

We study a particular generalisation of the classical Kramers model describing Brownian particles in the external potential. The generalised model includes the stochastic force which is modelled as an additive random noise that depends upon…

Statistical Mechanics · Physics 2010-09-09 Vlad Bezuglyy

Understanding the generalization abilities of modern machine learning algorithms has been a major research topic over the past decades. In recent years, the learning dynamics of Stochastic Gradient Descent (SGD) have been related to…

Machine Learning · Statistics 2023-12-04 Benjamin Dupuis , Paul Viallard

We address tracking and prediction of multiple moving objects in visual data streams as inference and sampling in a disentangled latent state-space model. By encoding objects separately and including explicit position information in the…

Machine Learning · Statistics 2019-10-15 Adnan Akhundov , Maximilian Soelch , Justin Bayer , Patrick van der Smagt

Pervasive across diverse domains, stochastic systems exhibit fluctuations in processes ranging from molecular dynamics to climate phenomena. The Langevin equation has served as a common mathematical model for studying such systems, enabling…

Statistical Mechanics · Physics 2025-05-01 Youngkyoung Bae , Seungwoong Ha , Hawoong Jeong

We revisit the Markov approximation necessary to derive ordinary Brownian motion from a model widely adopted in literature for this specific purpose. We show that this leads to internal inconsistencies, thereby implying that further search…

Quantum Physics · Physics 2009-10-31 A. Rocco , P. Grigolini

Stacked generalization is a general method of using a high-level model to combine lower-level models to achieve greater predictive accuracy. In this paper we address two crucial issues which have been considered to be a `black art' in…

Artificial Intelligence · Computer Science 2011-05-30 K. M. Ting , I. H. Witten

These notes give a summary of techniques used in large deviation theory to study the fluctuations of time-additive quantities, called dynamical observables, defined in the context of Langevin-type equations, which model equilibrium and…

Statistical Mechanics · Physics 2022-12-29 Hugo Touchette

Despite the extreme popularity of deep learning in science and industry, its formal understanding is limited. This thesis puts forth notions of rank as key for developing a theory of deep learning, focusing on the fundamental aspects of…

Machine Learning · Computer Science 2024-12-31 Noam Razin

By considering an ensemble of Brownian particles suspended in a heat bath as a thermodynamic system with an internal degree of freedom it is possible to obtain the Fokker-Planck equation for Brownian motion in a temperature gradient, by…

Condensed Matter · Physics 2007-05-23 A. Perez-Madrid , J. M. Rubi , P. Mazur

The Cartesian reverse derivative is a categorical generalization of reverse-mode automatic differentiation. We use this operator to generalize several optimization algorithms, including a straightforward generalization of gradient descent…

Optimization and Control · Mathematics 2021-09-22 Dan Shiebler

We propose a Lorentz-covariant theory of gravity, and explain its theoretical origins in the problem of time in Newtonian physics. In this retarded gravitation theory (RGT), the gravitational force depends upon both retarded position and…

General Physics · Physics 2015-05-27 C. K. Raju

The basic concepts of gravitational microlensing are introduced. We start with the lens equation, and then derive the image positions and magnifications. The statistical quantities of optical depth and event rate are then described. We…

Astrophysics · Physics 2008-11-05 Shude Mao

The general theory of Grothendieck categories is presented. We systemize the principle methods and results of the theory, showing how these results can be used for studying rings and modules.

Category Theory · Mathematics 2007-05-23 Grigory Garkusha