Cover Image

Learning time-scales in two-layers neural networks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Berthier, Raphaël, Montanari, Andrea, Zhou, Kangjie
Format:	Preprint
Published:	2023
Subjects:	Machine Learning Optimization and Control 34E15, 37N40, 68T07
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

On the dynamics of three-layer neural networks: initial condensation
by: Chen, Zheng-An, et al.
Published: (2024)

Terminally constrained flow-based generative models from an optimal control perspective
by: Gao, Weiguo, et al.
Published: (2026)

Cluster-based classification with neural ODEs via control
by: Álvarez-López, Antonio, et al.
Published: (2023)

Data Augmentation and Regularization for Learning Group Equivariance
by: Nordenfors, Oskar, et al.
Published: (2025)

Losing momentum in continuous-time stochastic optimisation
by: Jin, Kexin, et al.
Published: (2022)

Optimization Dynamics of Equivariant and Augmented Neural Networks
by: Nordenfors, Oskar, et al.
Published: (2023)

A Learning Stability Profile for Finite-Dimensional Learning Dynamics
by: Katende, Ronald
Published: (2025)

Diagonal Linear Networks and the Lasso Regularization Path
by: Berthier, Raphaël
Published: (2025)

Non-Asymptotic Analysis of Projected Gradient Descent for Physics-Informed Neural Networks
by: Nießen, Jonas, et al.
Published: (2025)

Stability properties of Minimal Gated Unit neural networks
by: De Carli, Stefano, et al.
Published: (2026)

SympFormer: Accelerated attention blocks via Inertial Dynamics on Density Manifolds
by: Stein, Viktor, et al.
Published: (2026)

Primal-dual dynamical systems with closed-loop control for convex optimization in continuous and discrete time
by: Zhang, Huan, et al.
Published: (2026)

Localmax dynamics for attention in transformers and its asymptotic behavior
by: Cimetière, Henri, et al.
Published: (2025)

Which exceptional low-dimensional projections of a Gaussian point cloud can be found in polynomial time?
by: Montanari, Andrea, et al.
Published: (2024)

OCTANE -- Optimal Control for Tensor-based Autoencoder Network Emergence: Explicit Case
by: Khatri, Ratna, et al.
Published: (2025)

Tikhonov regularization of second-order plus first-order primal-dual dynamical systems for separable convex optimization
by: Sun, Xiangkai, et al.
Published: (2024)

Inertial dynamical systems and accelerated algorithms with implicit Hessian-driven damping for nonconvex optimization
by: Gao, Zeying, et al.
Published: (2026)

Inertial accelerated primal-dual algorithms for non-smooth convex optimization problems with linear equality constraints
by: Zhang, Huan, et al.
Published: (2025)

Convergence analysis of a Tikhonov regularized inertial dynamical system and algorithm for convex optimization problems
by: Sun, Xiangkai, et al.
Published: (2025)

Fractional-Boundary-Regularized Deep Galerkin Method for Variational Inequalities in Mixed Optimal Stopping and Control
by: Zhao, Yun, et al.
Published: (2025)

Reduced-order modeling of Hamiltonian dynamics based on symplectic neural networks
by: Chen, Yongsheng, et al.
Published: (2025)

Tikhonov regularized inertial primal-dual dynamics for convex-concave bilinear saddle point problems
by: Sun, Xiangkai, et al.
Published: (2024)

Physics-informed nonlinear vector autoregressive models for the prediction of dynamical systems
by: Adler, James H., et al.
Published: (2024)

Coordinate-independent model reductions of chemical reaction networks based on geometric singular perturbation theory
by: Lapuz, Timothy Earl Figueroa, et al.
Published: (2025)

Nonintegrability of the restricted three-body problem
by: Yagasaki, Kazuyuki
Published: (2021)

Nesterov acceleration for strongly convex-strongly concave bilinear saddle point problems: discrete and continuous-time approaches
by: He, Xin, et al.
Published: (2025)

Chaos-Free Networks are Stable Recurrent Neural Networks
by: De Carli, Stefano, et al.
Published: (2026)

The Legacy of the Cartwright-Littlewood Collaboration
by: Guckenheimer, John
Published: (2025)

Convergence, design and training of continuous-time dropout as a random batch method
by: Álvarez-López, Antonio, et al.
Published: (2025)

Mathematical modelling of the vitamin C clock reaction: a study of two kinetic regimes
by: Alsaleh, Aliya, et al.
Published: (2024)

Phase space integrity in neural network models of Hamiltonian dynamics: A Lagrangian descriptor approach
by: Hasmi, Abrari Noor, et al.
Published: (2026)

Explicit neural network classifiers for non-separable data
by: Ewald, Patrícia Muñoz
Published: (2025)

A Low-complexity Structured Neural Network to Realize States of Dynamical Systems
by: Aluvihare, Hansaka, et al.
Published: (2025)

System stabilization with policy optimization on unstable latent manifolds
by: Werner, Steffen W. R., et al.
Published: (2024)

Constructive Universal Approximation and Finite Sample Memorization by Narrow Deep ReLU Networks
by: Hernández, Martín, et al.
Published: (2024)

Understanding broad-spike oscillations in a model of intracellular calcium dynamics
by: Rahmani, Behnaz, et al.
Published: (2024)

Simulating Fokker-Planck equations via mean field control of score-based normalizing flows
by: Zhou, Mo, et al.
Published: (2025)

Inertial primal-dual dynamics with Hessian-driven damping and Tikhonov regularization for convex-concave bilinear saddle point problems
by: Sun, Xiangkai, et al.
Published: (2024)

Robust Constrained Optimization via Sliding Mode Control
by: Kamal, Shyam, et al.
Published: (2026)

Ergodicity in planar slow-fast systems through slow relation functions
by: Huzak, Renato, et al.
Published: (2024)