Imagen de Portada

An extrapolated and provably convergent algorithm for nonlinear matrix decomposition with the ReLU function

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Gillis, Nicolas, Porcelli, Margherita, Seraghiti, Giovanni
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Image and Video Processing Optimization and Control 15A23, 65F55, 68Q25, 90C26, 65K05
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

prunAdag: an adaptive pruning-aware gradient method
por: Porcelli, Margherita, et al.
Publicado: (2025)

Stiefel optimization is NP-hard
por: Lai, Zehua, et al.
Publicado: (2025)

Kinetic description and convergence analysis of genetic algorithms for global optimization
por: Borghi, Giacomo, et al.
Publicado: (2023)

Grassmannian optimization is NP-hard
por: Lai, Zehua, et al.
Publicado: (2024)

Digital $n-$Manifolds With Or Without Boundaries
por: İs, Melih, et al.
Publicado: (2024)

Consensus-based optimization for closed-box adversarial attacks and a connection to evolution strategies
por: Roith, Tim, et al.
Publicado: (2025)

A Symplectic Discretization Based Proximal Point Algorithm for Convex Minimization
por: Yuan, Ya-xiang, et al.
Publicado: (2024)

Enhancing training of physics-informed neural networks using domain-decomposition based preconditioning strategies
por: Kopaničáková, Alena, et al.
Publicado: (2023)

On Maximum-a-Posteriori estimation with Plug & Play priors and stochastic gradient descent
por: Laumont, Rémi, et al.
Publicado: (2022)

Minimal dispersion on the cube and the torus
por: Arman, Andrii, et al.
Publicado: (2024)

Riemannian Adaptive Regularized Newton Methods with Hölder Continuous Hessians
por: Zhang, Chenyu, et al.
Publicado: (2023)

Random domain decomposition for parabolic PDEs on graphs
por: Hernández, Martín
Publicado: (2025)

Mixed precision HODLR matrices
por: Carson, Erin, et al.
Publicado: (2024)

Hybrid hierarchical matrices with adaptive mixed precision storage
por: Khan, Ritesh, et al.
Publicado: (2026)

Low-rank approximation of parameter-dependent matrices via CUR decomposition
por: Park, Taejun, et al.
Publicado: (2024)

A quantum-inspired multi-level tensor-train monolithic space-time method for nonlinear PDEs
por: Rapaka, N. R., et al.
Publicado: (2026)

A preconditioned difference of convex functions algorithm with extrapolation and line search
por: Zhang, Ran, et al.
Publicado: (2025)

The dependency of spectral gaps on the convergence of the inverse iteration for a nonlinear eigenvector problem
por: Henning, Patrick
Publicado: (2022)

Minimization Over the Nonconvex Sparsity Constraint Using A Hybrid First-order method
por: Yang, Xiangyu, et al.
Publicado: (2021)

Preconditioned Low-Rank Riemannian Optimization for Symmetric Positive Definite Linear Matrix Equations
por: Bioli, Ivan, et al.
Publicado: (2024)

Swarm-based optimization with jumps: a kinetic BGK framework and convergence analysis
por: Borghi, Giacomo, et al.
Publicado: (2025)

Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense
por: Ackermann, Julia, et al.
Publicado: (2023)

Recursive Bound-Constrained AdaGrad with Applications to Multilevel and Domain Decomposition Minimization
por: Gratton, Serge, et al.
Publicado: (2025)

Two-level overlapping additive Schwarz preconditioner for training scientific machine learning applications
por: Lee, Youngkyu, et al.
Publicado: (2024)

Bayesian imaging using Plug & Play priors: when Langevin meets Tweedie
por: Laumont, Rémi, et al.
Publicado: (2021)

An optimally fast objective-function-free minimization algorithm using random subspaces
por: Bellavia, S., et al.
Publicado: (2023)

Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for space-time solutions of semilinear partial differential equations
por: Ackermann, Julia, et al.
Publicado: (2024)

A Fast Monte Carlo algorithm for evaluating matrix functions with application in complex networks
por: Guidotti, Nicolas L., et al.
Publicado: (2023)

Optimization on the Oblique Manifold for Sparse Simplex Constraints via Multiplicative Updates
por: Esposito, Flavia, et al.
Publicado: (2025)

Accuracy and Stability of CUR decompositions with Oversampling
por: Park, Taejun, et al.
Publicado: (2024)

When can forward stable algorithms be composed stably?
por: Beltrán, Carlos, et al.
Publicado: (2021)

Computing nonlinear Schrödinger equations with Hermite functions beyond harmonic traps
por: Banica, Valeria, et al.
Publicado: (2025)

Fast Reflected Forward-Backward algorithm: achieving fast convergence rates for convex optimization with linear cone constraints
por: Bot, Radu Ioan, et al.
Publicado: (2024)

Randomized block-Krylov subspace methods for low-rank approximation of matrix functions
por: Persson, David, et al.
Publicado: (2025)

Convergence analysis of the transformed gradient projection algorithms on compact matrix manifolds
por: Ding, Wentao, et al.
Publicado: (2024)

Worst-Case Learning under a Multi-fidelity Model
por: Foucart, Simon, et al.
Publicado: (2024)

The rate of convergence of Bregman proximal methods: Local geometry vs. regularity vs. sharpness
por: Azizian, Waïss, et al.
Publicado: (2022)

Memory- and compute-optimized geometric multigrid GMGPolar for curvilinear coordinate representations -- Applications to fusion plasma
por: Litz, Julian, et al.
Publicado: (2025)

Sample-wise Constrained Learning via a Sequential Penalty Approach with Applications in Image Processing
por: Lanzillotta, Francesca, et al.
Publicado: (2026)

On the algorithmic construction of deep ReLU networks
por: Huybrechs, Daan
Publicado: (2025)