Image de couverture de livre

Grassmannian Geometry and Global Convergence of Variable Projection for Neural Networks

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Dus, Mathias
Format:	Preprint
Publié:	2026
Sujets:	Optimization and Control
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Wasserstein Formulation of Reinforcement Learning. An Optimal Transport Perspective on Policy Optimization
par: Dus, Mathias
Publié: (2026)

Two-layers neural networks for Schr{ö}dinger eigenvalue problems
par: Dus, Mathias, et autres
Publié: (2024)

Comparison between tensor methods and neural networks in electronic structure calculations
par: Dus, Mathias, et autres
Publié: (2024)

A Globally Convergent Algorithm for Neural Network Parameter Optimization Based on Difference-of-Convex Functions
par: Tschernutter, Daniel, et autres
Publié: (2024)

On Exponential Convergence of Random Variables
par: Tarłowski, Dawid
Publié: (2024)

Physics-Informed Neural Network Policy Iteration: Algorithms, Convergence, and Verification
par: Meng, Yiming, et autres
Publié: (2024)

Global Convergence of SGD On Two Layer Neural Nets
par: Gopalani, Pulkit, et autres
Publié: (2022)

A Fast and Convergent Algorithm for Unassigned Distance Geometry Problems
par: Fan, Jun, et autres
Publié: (2025)

Information Geometry of Exponentiated Gradient: Convergence beyond L-Smoothness
par: Elshiaty, Yara, et autres
Publié: (2025)

Over-parameterised Shallow Neural Networks with Asymmetrical Node Scaling: Global Convergence Guarantees and Feature Learning
par: Caron, Francois, et autres
Publié: (2023)

Min-Max Grassmannian Optimization for Online Subspace Tracking
par: Bharadwaj, Shreyas, et autres
Publié: (2026)

Inexact Projected Preconditioned Gradient Methods with Variable Metrics: General Convergence Theory via Lyapunov Approach
par: Guo, Ruchi, et autres
Publié: (2025)

Temporal Variabilities Limit Convergence Rates in Gradient-Based Online Optimization
par: Van Scoy, Bryan, et autres
Publié: (2025)

Convergence Rate Analysis of SOAP with Arbitrary Orthogonal Projection Matrices
par: Li, Huan, et autres
Publié: (2026)

On the Convergence of Projected Policy Gradient for Any Constant Step Sizes
par: Liu, Jiacai, et autres
Publié: (2023)

A Quadratically Convergent Alternating Projection Method for Nonconvex Sets
par: Xiao, Nachuan, et autres
Publié: (2025)

Solving Inverse Problems with Deep Linear Neural Networks: Global Convergence Guarantees for Gradient Descent with Weight Decay
par: Laus, Hannah, et autres
Publié: (2025)

Global Convergence of SGD For Logistic Loss on Two Layer Neural Nets
par: Gopalani, Pulkit, et autres
Publié: (2023)

GREAT: Grassmannian REcursive Algorithm for Tracking & Online System Identification
par: Sasfi, András, et autres
Publié: (2024)

Global Nonconvex Optimization with Integer Variables
par: Bertsimas, Dimitris, et autres
Publié: (2025)

OPTAMI: Global Superlinear Convergence of High-order Methods
par: Kamzolov, Dmitry, et autres
Publié: (2024)

Distributed Adaptive Time-Varying Optimization with Global Asymptotic Convergence
par: Jiang, Liangze, et autres
Publié: (2024)

Globally-Constrained Decentralized Optimization with Variable Coupling
par: Wang, Dandan, et autres
Publié: (2024)

Explicit Global Convergence Rates of BFGS without Line Search
par: Yu, Jianjiang, et autres
Publié: (2025)

Linear Convergence Results for Inertial Type Projection Algorithm for Quasi-Variational Inequalities
par: Yao, Yonghong, et autres
Publié: (2024)

The Convex Geometry of Network Flows
par: Diamandis, Theo, et autres
Publié: (2024)

Global Convergence of Control-Based Lagrangian Flows for Non-Convex Optimization
par: Pirrera, Simone, et autres
Publié: (2026)

On the (almost) Global Exponential Convergence of the Overparameterized Policy Optimization for the LQR Problem
par: Wafi, Moh Kamalul, et autres
Publié: (2025)

Convergence Analysis for Learning Orthonormal Deep Linear Neural Networks
par: Qin, Zhen, et autres
Publié: (2023)

Plugging Weight-tying Nonnegative Neural Network into Proximal Splitting Method: Architecture for Guaranteeing Convergence to Optimal Point
par: Shimizu, Haruya, et autres
Publié: (2025)

Global Convergence and Error Propagation in Neural Gradient Flows: A Riemannian Optimization Framework
par: Zheng, Shixin, et autres
Publié: (2026)

The Two Lives of the Grassmannian
par: Devriendt, Karel, et autres
Publié: (2024)

Sketch-and-Project Meets Newton Method: Global $\mathcal O(k^{-2})$ Convergence with Low-Rank Updates
par: Hanzely, Slavomír
Publié: (2023)

Global Optimization for Combinatorial Geometry Problems Revisited in the Era of LLMs
par: Berthold, Timo, et autres
Publié: (2026)

First-Order Projected Algorithms With the Same Linear Convergence Rate Bounds as Their Unconstrained Counterparts
par: Li, Mengmou, et autres
Publié: (2025)

Non-asymptotic Global Convergence Rates of BFGS with Exact Line Search
par: Jin, Qiujiang, et autres
Publié: (2024)

Global Convergence Analysis of the Power Proximal Point and Augmented Lagrangian Method
par: Oikonomidis, Konstantinos A., et autres
Publié: (2023)

INTHOP: A Second-Order Globally Convergent Method for Nonconvex Optimization
par: Kumar, Krishan, et autres
Publié: (2025)

Global Convergence of Oja's Component Flow for General Square Matrices and Its Applications
par: Tsuzuki, Daiki, et autres
Publié: (2025)

Policy Gradient Methods for the Cost-Constrained LQR: Strong Duality and Global Convergence
par: Zhao, Feiran, et autres
Publié: (2024)