English
Related papers

Related papers: On microscopic origins of generalized gradient str…

200 papers

An open question in the Deep Learning community is why neural networks trained with Gradient Descent generalize well on real datasets even though they are capable of fitting random data. We propose an approach to answering this question…

Machine Learning · Computer Science 2020-02-26 Satrajit Chatterjee

We consider generalized gradient systems in Banach spaces whose evolutions are generated by the interplay between an energy functional and a dissipation potential. We focus on the case in which the dual dissipation potential is given by a…

Analysis of PDEs · Mathematics 2023-08-01 Alexander Mielke , Riccarda Rossi , Artur Stephan

The present paper is aimed at studying the microscopic origin of the jump diffusion. Starting from the $N$-body Liouville equation and making only the assumption that molecular reorientation is overdamped, we derive and solve the new…

Statistical Mechanics · Physics 2009-07-03 M. F. Gelin , D. S. Kosov

Recent developments in Macroscopic Fluctuation Theory show that many interacting particle systems behave macroscopically as a combination of a gradient flow with Hamiltonian dynamics. This observation leads to the natural question how these…

Mathematical Physics · Physics 2024-02-07 D. R. Michiel Renger

We construct a stochastic model showing the relationship between noise, gradient flows and rate-independent systems. The model consists of a one-dimensional birth-death process on a lattice, with rates derived from Kramers' law as an…

Mathematical Physics · Physics 2015-09-30 Giovanni A. Bonaschi , Mark A. Peletier

A major challenge in understanding the generalization of deep learning is to explain why (stochastic) gradient descent can exploit the network architecture to find solutions that have good generalization performance when using high capacity…

Machine Learning · Computer Science 2019-02-12 Yifan Wu , Barnabas Poczos , Aarti Singh

In this work, we investigate links between the formulation of the flow of marginals of reversible diffusion processes as gradient flows in the space of probability measures and path wise large deviation principles for sequences of such…

Probability · Mathematics 2014-05-16 Max Fathi

Based on laboratory based growth of plant-like structures from inorganic materials, we present new theory for the emergence of plant structure at a range of scales dictated by levels of ionization (charge density), which can be traced…

General Physics · Physics 2017-01-24 Philip Turner , Laurent Nottale

A system far from equilibrium is characterized by unconventional many-body dynamical effects, which can lead to anomalous density fluctuations and mass transport. Interestingly, these structural and dynamic features often emerge…

Statistical Mechanics · Physics 2010-03-09 David A. Head , Hajime Tanaka

Morphogen gradients play an essential role in the spatial regulation of cell patterning during early development. The classical mechanism of morphogen gradient formation involves the diffusion of morphogens away from a localized source…

Statistical Mechanics · Physics 2022-11-09 Paul C Bressloff

Complex physical dynamics can often be modeled as a Markov jump process between mesoscopic configurations. When jumps between mesoscopic states are mediated by thermodynamic reservoirs, the time-irreversibility of the jump process is a…

Statistical Mechanics · Physics 2017-04-12 Todd R. Gingrich , Grant M. Rotskoff , Jordan M. Horowitz

In the first part of this paper, we consider a family of continuous-time dynamical systems coupled with diffusion-transmutation processes. Under certain conditions, such randomly perturbed dynamical systems can be interpreted as an averaged…

Optimization and Control · Mathematics 2024-08-21 Getachew K. Befekadu

Starting from certain causality conditions and a discrete form of general covariance, we derive a very general family of classically stochastic, sequential growth dynamics for causal sets. The resulting theories provide a relatively…

General Relativity and Quantum Cosmology · Physics 2011-05-05 D. P. Rideout , R. D. Sorkin

A large deviation principle is established for a two-scale stochastic system in which the slow component is a continuous process given by a small noise finite dimensional It\^{o} stochastic differential equation, and the fast component is a…

Probability · Mathematics 2017-05-09 Amarjit Budhiraja , Paul Dupuis , Arnab Ganguly

A foundational question in relativistic fluid mechanics concerns the properties of the hydrodynamic gradient expansion at large orders. We establish the precise conditions under which this gradient expansion diverges for a broad class of…

High Energy Physics - Theory · Physics 2021-09-08 Michal P. Heller , Alexandre Serantes , Michał Spaliński , Viktor Svensson , Benjamin Withers

Much of the structure of macroscopic evolution equations for relaxation to equilibrium can be derived from symmetries in the dynamical fluctuations around the most typical trajectory. For example, detailed balance as expressed in terms of…

Statistical Mechanics · Physics 2018-04-12 Richard Kraaij , Alexandre Lazarescu , Christian Maes , Mark Peletier

We consider temporal models of rapidly changing Markovian networks modulated by time-evolving spatially dependent kernels that define rates for edge formation and dissolution. Alternatively, these can be viewed as Markovian networks with…

Probability · Mathematics 2025-06-11 Shankar Bhamidi , Amarjit Budhiraja , Souvik Ray

In this paper, the inherent gradient flow structures of thermo-poro-visco-elastic processes in porous media are examined for the first time. In the first part, a modelling framework is introduced aiming for describing such processes as…

Numerical Analysis · Mathematics 2019-11-27 Jakub Wiktor Both , Kundan Kumar , Jan Martin Nordbotten , Florin Adrian Radu

The notion of dissipative dynamical systems provides a formal description of processes that cannot generate energy internally. For these systems, changes in energy can only occur due to an external energy supply or dissipation effects.…

Numerical Analysis · Mathematics 2026-02-18 Attila Karsai , Philipp Schulze

Self-organization through noisy interactions is ubiquitous across physics, mathematics, and machine learning, yet how long-range structure emerges from local noisy dynamics remains poorly understood. Here, we investigate three paradigmatic…

Soft Condensed Matter · Physics 2026-03-31 Satyam Anand , Guanming Zhang , Stefano Martiniani