English
Related papers

Related papers: Gradient Flows and Nonlinear Power Methods for the…

200 papers

Variational interpolants are an indispensable tool for the construction of gradient-flow solutions via the Minimizing Movement Scheme. The De Giorgi lemma provides the associated discrete energy-dissipation inequality. It was originally…

Analysis of PDEs · Mathematics 2026-03-19 Alexander Mielke , Riccarda Rossi

We study the implicit regularization imposed by gradient descent for learning multi-layer homogeneous functions including feed-forward fully connected and convolutional deep neural networks with linear, ReLU or Leaky ReLU activation. We…

Machine Learning · Computer Science 2018-11-01 Simon S. Du , Wei Hu , Jason D. Lee

In this article, the existence of the spectrum (the eigenvalues) for the nonlinear continuous operators acting in the Banach spaces is investigated. For the study, this question is used a different approach that allows the studying of all…

Functional Analysis · Mathematics 2023-10-11 Kamal N. Soltanov

We study non-convex subgradient flows for training two-layer ReLU neural networks from a convex geometry and duality perspective. We characterize the implicit bias of unregularized non-convex gradient flow as convex regularization of an…

Machine Learning · Computer Science 2021-10-14 Yifei Wang , Mert Pilanci

In this paper, we propose novel algorithms integrated projection-free techniques with accelerated gradient flows to minimize bending energies for nonlinear plates with non-convex metric constraints. We discuss the stability and constraint…

Numerical Analysis · Mathematics 2025-06-18 Guozhi Dong , Hailong Guo , Shuo Yang

We derive explicit equations governing the cumulative biases and weights in Deep Learning with ReLU activation function, based on gradient descent for the Euclidean cost in the input layer, and under the assumption that the weights are, in…

Machine Learning · Computer Science 2025-01-15 Thomas Chen

In proper, geodesic Gromov hyperbolic spaces, we investigate discrete-time gradient flows via the proximal point algorithm for unbounded Lipschitz convex functions. Assuming that the target convex function has negative asymptotic slope…

Optimization and Control · Mathematics 2025-10-24 Shin-ichi Ohta

This paper presents and investigates an inexact proximal gradient method for solving composite convex optimization problems characterized by an objective function composed of a sum of a full-domain differentiable convex function and a…

Optimization and Control · Mathematics 2025-04-16 Yunier Bello-Cruz , Max L. N. Gonçalves , Jefferson G. Melo , Cassandra Mohr

In this paper, we study the asymptotic behavior of continuous- and discrete-time gradient flows of a ``lower-unbounded" convex function $f$ on a Hadamard manifold $M$, particularly, their convergence properties to the boundary $M^{\infty}$…

Optimization and Control · Mathematics 2026-03-31 Hiroshi Hirai , Keiya Sakabe

We introduce a new framework to deal with rough differential equations based on flows and their approximations. Our main result is to prove that measurable flows exist under weak conditions, even solutions to the corresponding rough…

Probability · Mathematics 2019-05-17 Antoine Brault , Antoine Lejay

We explicitly construct parameter transformations between gradient flows in metric spaces, called curves of maximal slope, having different exponents when the associated function satisfies a suitable convexity condition. These…

Analysis of PDEs · Mathematics 2024-04-04 Sho Shimoyama

In this work, we develop an $\mathcal{O}(N)$ implicit real space method in 1D and 2D for the Cahn Hilliard (CH) and vector Cahn Hilliard (VCH) equations, based on the Method Of Lines Transpose (MOL$^\text{T}$) formulation. This formulation…

Numerical Analysis · Mathematics 2016-11-15 Matthew Causley , Hana Cho , Andrew Christlieb

Convolutional neural networks are widely used in imaging and image recognition. Learning such networks from training data leads to the minimization of a non-convex function. This makes the analysis of standard optimization methods such as…

Optimization and Control · Mathematics 2026-01-14 Jona-Maria Diederen , Holger Rauhut , Ulrich Terstiege

Composite optimization problems, where the sum of a smooth and a merely lower semicontinuous function has to be minimized, are often tackled numerically by means of proximal gradient methods as soon as the lower semicontinuous part of the…

Optimization and Control · Mathematics 2022-07-05 Christian Kanzow , Patrick Mehlitz

We consider the proximal-gradient method for minimizing an objective function that is the sum of a smooth function and a non-smooth convex function. A feature that distinguishes our work from most in the literature is that we assume that…

Optimization and Control · Mathematics 2022-11-07 Yutong Dai , Daniel P. Robinson

We prove an implicit function theorem for functions on infinite-dimensional Banach manifolds, invariant under the (local) action of a finite dimensional Lie group. Motivated by some geometric variational problems, we consider group actions…

Differential Geometry · Mathematics 2015-02-10 Renato G. Bettiol , Paolo Piccione , Gaetano Siciliano

In this work, we present a new approach to analyze the gradient flow for a positive semi-definite matrix denoising problem in an extensive-rank and high-dimensional regime. We use recent linear pencil techniques of random matrix theory to…

Machine Learning · Statistics 2023-03-17 Antoine Bodin , Nicolas Macris

This article overviews how gradient flows, and discretizations thereof, are useful to design and analyze optimization and sampling algorithms. The interplay between optimization, sampling, and gradient flows is an active research area; our…

Computation · Statistics 2023-02-23 N. Garcia Trillos , B. Hosseini , D. Sanz-Alonso

We present a framework to calculate large deviations for nonlinear functions of independent random variables supported on compact sets in Banach spaces, by extending the result in Chatterjee and Dembo [6]. Previous research on nonlinear…

Probability · Mathematics 2018-07-12 Jun Yan

We investigate the renormalization group (RG) structure of the gradient flow. Instead of using the original bare action to generate the flow, we propose to use the effective action at each flow time. We write down the basic equation for…

High Energy Physics - Theory · Physics 2019-12-06 Yoshihiko Abe , Masafumi Fukuma