English
Related papers

Related papers: Gradient Flow in Morse and Analytic Settings

200 papers

We propose new limiting dynamics for stochastic gradient descent in the small learning rate regime called stochastic modified flows. These SDEs are driven by a cylindrical Brownian motion and improve the so-called stochastic modified…

Probability · Mathematics 2023-02-15 Benjamin Gess , Sebastian Kassing , Vitalii Konarovskyi

Gradient-based learning in multi-layer neural networks displays a number of striking features. In particular, the decrease rate of empirical risk is non-monotone even after averaging over large batches. Long plateaus in which one observes…

Machine Learning · Computer Science 2025-03-25 Raphaël Berthier , Andrea Montanari , Kangjie Zhou

Many theoretical studies on neural networks attribute their excellent empirical performance to the implicit bias or regularization induced by first-order optimization algorithms when training networks under certain initialization…

Machine Learning · Computer Science 2025-08-29 Hancheng Min , René Vidal

The Yang-Mills gradient flow in finite volume is used to define a running coupling scheme. As our main result the discrete beta-function, or step scaling function, is calculated for scale change s=3/2 at several lattice spacings for SU(3)…

High Energy Physics - Lattice · Physics 2012-11-15 Zoltan Fodor , Kieran Holland , Julius Kuti , Daniel Nogradi , Chik Him Wong

Turbulent flow fields can be expanded into a series in a set of basic functions. The terms of such series are often called modes. A master- (or determining) mode set is a subset of these modes, the time history of which uniquely determines…

Fluid Dynamics · Physics 2008-09-18 Sergei Chernyshenko , Maksym Bondarenko

In this paper we consider the steepest descent L2-gradient flow of the entropy functional. The flow expands convex curves, with the radius of an initial circle growing like the square root of time. Our main result is that, for any initial…

Differential Geometry · Mathematics 2023-04-20 Lachlann O'Donnell , Glen Wheeler , Valentina-Mira Wheeler

We discuss $(K,N)$-convexity and gradient flows for $(K,N)$-convex functionals on metric spaces, in the case of real $K$ and negative $N$. In this generality, it is necessary to consider functionals unbounded from below and/or above,…

Functional Analysis · Mathematics 2026-05-25 Lorenzo Dello Schiavo , Mattia Magnabosco , Chiara Rigoni

We use gradient flow to compute the static force based on a Wilson loop with a chromoelectric field insertion. The result can be compared on one hand to the static force from the numerical derivative of the lattice static energy, and on the…

High Energy Physics - Lattice · Physics 2022-12-26 Nora Brambilla , Viljami Leino , Julian Mayer-Steudte , Antonio Vairo

We develop the theory of fractional gradient flows: an evolution aimed at the minimization of a convex, l.s.c.~energy, with memory effects. This memory is characterized by the fact that the negative of the (sub)gradient of the energy equals…

Analysis of PDEs · Mathematics 2021-01-05 Wenbo Li , Abner J. Salgado

We study the asymptotic behaviour of a gradient system in a regime in which the driving energy becomes singular. For this system gradient-system convergence concepts are ineffective. We characterize the limiting behaviour in a different…

Analysis of PDEs · Mathematics 2021-11-17 Mark A. Peletier , Mikola C. Schlottke

Prior flow matching methods in robotics have primarily learned velocity fields to morph one distribution of trajectories into another. In this work, we extend flow matching to capture second-order trajectory dynamics, incorporating…

Robotics · Computer Science 2025-03-11 Khang Nguyen , An T. Le , Tien Pham , Manfred Huber , Jan Peters , Minh Nhat Vu

This chapter describes how gradient flows and nonlinear power methods in Banach spaces can be used to solve nonlinear eigenvector-dependent eigenvalue problems, and how convergence of (discretized) approximations can be verified. We review…

Numerical Analysis · Mathematics 2022-03-15 Leon Bungert , Martin Burger

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

We study evolution equations on metric graphs with reservoirs, that is graphs where a one-dimensional interval is associated to each edge and, in addition, the vertices are able to store and exchange mass with these intervals. Focusing on…

Analysis of PDEs · Mathematics 2024-12-24 Georg Heinze , Jan-Frederik Pietschmann , André Schlichting

We report on the progress of our study on the color-electric correlation functions under gradient flow on the lattice. This calculation is the first step of our long-term project to estimate a series of important transport coefficients, of…

High Energy Physics - Lattice · Physics 2020-01-01 Luis Altenkort , Olaf Kaczmarek , Lukas Mazur , Hai-Tao Shu

We introduce action-driven flows for causal variational principles, being a class of non-convex variational problems emanating from applications in fundamental physics. In the compact setting, H\"older continuous curves of measures are…

Mathematical Physics · Physics 2026-05-27 Felix Finster , Franz Gmeineder

The results of this paper concern the Morse theory of the norm-square of the moment map on the space of representations of a quiver. We show that the gradient flow of this function converges, and that the Morse stratification induced by the…

Differential Geometry · Mathematics 2010-06-10 Megumi Harada , Graeme Wilkin

The evaluation and consideration of the mean flow in wave evolution equations are necessary for the accurate prediction of fluid particle trajectories under wave groups, with relevant implications in several domains, from the transport of…

This article considers some classes of models dealing with the dynamics of discrete curves subjected to stochastic deformations. It turns out that the problems of interest can be set in terms of interacting exclusion processes, the ultimate…

Probability · Mathematics 2012-01-26 Guy Fayolle , Cyril Furtlehner

The gradient flow is a valuable tool for the lattice community, with applications from scale-setting to implementing chiral fermions. Here I focus on the gradient flow as a means to suppress power-divergent mixing. Power-divergent mixing…

High Energy Physics - Lattice · Physics 2015-12-02 Christopher Monahan
‹ Prev 1 4 5 6 7 8 10 Next ›