English
Related papers

Related papers: Gradient extremals, talwegs, valleys, and directio…

200 papers

This paper considers the problem of solving systems of quadratic equations, namely, recovering an object of interest $\mathbf{x}^{\natural}\in\mathbb{R}^{n}$ from $m$ quadratic equations/samples…

Machine Learning · Statistics 2019-06-13 Yuxin Chen , Yuejie Chi , Jianqing Fan , Cong Ma

We are interested in existence of gradient flows for shape functionals especially for first Laplacian eigenvalues. We introduce different techniques to prove existence and use different formulations for gradient flows. We apply a…

Spectral Theory · Mathematics 2020-03-04 Yannick Holle

Recent works exploring the training dynamics of homogeneous neural network weights under gradient flow with small initialization have established that in the early stages of training, the weights remain small and near the origin, but…

Machine Learning · Computer Science 2025-05-19 Akshay Kumar , Jarvis Haupt

In a Hilbert setting, for convex differentiable optimization, we develop a general framework for adaptive accelerated gradient methods. They are based on damped inertial dynamics where the coefficients are designed in a closed-loop way.…

Optimization and Control · Mathematics 2025-01-28 Hedy Attouch , Radu Ioan Bot , Dang-Khoa Nguyen

We rigorously study the relation between the training dynamics via stochastic gradient descent (SGD) and the spectra of empirical Hessian and gradient matrices. We prove that in two canonical classification tasks for multi-class…

Machine Learning · Computer Science 2025-05-19 Gerard Ben Arous , Reza Gheissari , Jiaoyang Huang , Aukosh Jagannath

We associate curves of isotropic, Lagrangian and coisotropic subspaces to higher order, one parameter variational problems. Minimality and conjugacy properties of extremals are described in terms of these curves.

Symplectic Geometry · Mathematics 2015-10-12 C. Durán , D. Otero

In the theory of so called "Covariant Quantum Mechanics" a basic role is played by Hermitian vector fields on a complex line bundle in the frameworks of Galilei and Einstein spacetimes. In fact, it has been proved that the Lie algebra of…

Mathematical Physics · Physics 2007-05-23 Josef Janyška , Marco Modugno

Gradient descent-ascent (GDA) flows play a central role in finding saddle points of bivariate functionals, with applications in optimization, game theory, and robust control. While they are well-understood in Hilbert and Banach spaces via…

Functional Analysis · Mathematics 2025-06-26 Noboru Isobe , Sho Shimoyama

Various questions related to distances between vertices of simple, finite graphs are of interest to extremal graph theorists. The Steiner distance of a set of $k$ vertices is a natural generalization of the regular distance. We extend…

Combinatorics · Mathematics 2023-02-07 Hua Wang , Andrew Zhang

Full-batch gradient descent on neural networks drives the largest Hessian eigenvalue to the threshold $2/\eta$, where $\eta$ is the learning rate. This phenomenon, the Edge of Stability, has resisted a unified explanation: existing accounts…

Machine Learning · Computer Science 2026-04-23 Elon Litman

The Hermitian eigenvalue problem asks for the possible eigenvalues of a sum of $n\times n$ Hermitian matrices, given the eigenvalues of the summands. The regular faces of the cones $\Gamma_n(s)$ controlling this problem have been…

Algebraic Geometry · Mathematics 2017-11-17 Prakash Belkale

We study the learning performance of gradient descent when the empirical risk is weakly convex, namely, the smallest negative eigenvalue of the empirical risk's Hessian is bounded in magnitude. By showing that this eigenvalue can control…

Machine Learning · Statistics 2021-06-02 Dominic Richards , Mike Rabbat

We investigate two-point velocity-gradient correlation functions in homogeneous isotropic turbulence using exact relations and direct numerical simulations. The second-order gradient correlation is shown to be exactly related to the…

Fluid Dynamics · Physics 2026-05-20 Anwesha Dey , Ritwik Mukherjee , Aikya Banerjee , Samriddhi Sankar Ray

We empirically demonstrate that full-batch gradient descent on neural network training objectives typically operates in a regime we call the Edge of Stability. In this regime, the maximum eigenvalue of the training loss Hessian hovers just…

Machine Learning · Computer Science 2022-11-24 Jeremy M. Cohen , Simran Kaur , Yuanzhi Li , J. Zico Kolter , Ameet Talwalkar

This work revolves around the rigorous asymptotic analysis of models in nonlocal hyperelasticity. The corresponding variational problems involve integral functionals depending on nonlocal gradients with a finite interaction range $\delta$,…

Analysis of PDEs · Mathematics 2024-04-30 Javier Cueto , Carolin Kreisbeck , Hidde Schönberger

This article deals with the conjugate gradient method on a Riemannian manifold with interest in global convergence analysis. The existing conjugate gradient algorithms on a manifold endowed with a vector transport need the assumption that…

Optimization and Control · Mathematics 2016-06-20 Hiroyuki Sato , Toshihiro Iwai

We develop new sub-optimality bounds for gradient descent (GD) that depend on the conditioning of the objective along the path of optimization rather than on global, worst-case constants. Key to our proofs is directional smoothness, a…

Machine Learning · Computer Science 2025-01-15 Aaron Mishkin , Ahmed Khaled , Yuanhao Wang , Aaron Defazio , Robert M. Gower

We prove the convergence of a Wasserstein gradient flow of a free energy in inhomogeneous media. Both the energy and media can depend on the spatial variable in a fast oscillatory manner. In particular, we show that the gradient-flow…

Analysis of PDEs · Mathematics 2025-08-19 Yuan Gao , Nung Kwan Yip

We prove a central limit theorem for the components of the largest eigenvectors of the adjacency matrix of a finite-dimensional random dot product graph whose true latent positions are unknown. In particular, we follow the methodology…

Statistics Theory · Mathematics 2013-12-24 Avanti Athreya , Vince Lyzinski , David J. Marchette , Carey E. Priebe , Daniel L. Sussman , Minh Tang

Wasserstein gradient flows have become a central tool for optimization problems over probability measures. A natural numerical approach is forward-Euler time discretization. We show, however, that even in the simple case where the energy…

Numerical Analysis · Mathematics 2025-10-16 Yewei Xu , Qin Li