Copertina

Designing Preconditioners for SGD: Local Conditioning, Noise Floors, and Basin Stability

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Scott, Mitchell, Xu, Tianshi, Tang, Ziyuan, Pichette-Emmons, Alexandra, Ye, Qiang, Saad, Yousef, Xi, Yuanzhe
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Numerical Analysis Machine Learning Primary 65K10, Secondary 68T05
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Anderson Acceleration with Truncated Gram-Schmidt
di: Tang, Ziyuan, et al.
Pubblicazione: (2024)

Neural Approximate Inverse Preconditioners
di: Xu, Tianshi, et al.
Pubblicazione: (2025)

Mixed Precision Orthogonalization-Free Projection Methods for Eigenvalue and Singular Value Problems
di: Xu, Tianshi, et al.
Pubblicazione: (2025)

Straggler-tolerant stationary methods for linear systems
di: Kalantzis, Vassilis, et al.
Pubblicazione: (2024)

Multiscale Neural Networks for Approximating Green's Functions
di: Hao, Wenrui, et al.
Pubblicazione: (2024)

Preconditioned Truncated Single-Sample Estimators for Scalable Stochastic Optimization
di: Xu, Tianshi, et al.
Pubblicazione: (2025)

A Spectral Preconditioner for the Conjugate Gradient Method with Iteration Budget
di: Diouane, Youssef, et al.
Pubblicazione: (2026)

A Randomized Algorithm for Preconditioner Selection
di: DiPaolo, Conner, et al.
Pubblicazione: (2019)

Neural Preconditioned Born Series: A Metric-Matched Framework for Learning-based Preconditioners
di: Wang, Juntao, et al.
Pubblicazione: (2026)

Hypernetwork-Conditioned WENO5 Conservative-Form CNNs for One-Dimensional Conservation Laws
di: Chen, Yongsheng, et al.
Pubblicazione: (2026)

Row-Splitting ILU Preconditioners for Sparse Least-Squares Problems
di: Scott, Jennifer, et al.
Pubblicazione: (2026)

An Adaptive Factorized Nyström Preconditioner for Regularized Kernel Matrices
di: Zhao, Shifan, et al.
Pubblicazione: (2023)

Learning a generalized multiscale prolongation operator
di: Liu, Yucheng, et al.
Pubblicazione: (2024)

Spectral-Refiner: Accurate Fine-Tuning of Spatiotemporal Fourier Neural Operator for Turbulent Flows
di: Cao, Shuhao, et al.
Pubblicazione: (2024)

NLTGCR: A class of Nonlinear Acceleration Procedures based on Conjugate Residuals
di: He, Huan, et al.
Pubblicazione: (2023)

Numerical Solution of Mixed-Dimensional PDEs Using a Neural Preconditioner
di: Dimola, Nunzio, et al.
Pubblicazione: (2025)

Numerical Instabilities in the Kaczmarz Method and Stabilization by Iterative Refinement
di: Dereziński, Michał, et al.
Pubblicazione: (2026)

Data-Free Asymptotics-Informed Operator Networks for Singularly Perturbed PDEs
di: Lee, Jinsil, et al.
Pubblicazione: (2025)

Data Completion for Electrical Impedance Tomography by Conditional Diffusion Models
di: Chen, Ke, et al.
Pubblicazione: (2026)

Recurrent Neural Operators: Stable Long-Term PDE Prediction
di: Ye, Zaijun, et al.
Pubblicazione: (2025)

RONOM: Reduced-Order Neural Operator Modeling
di: Dummer, Sven, et al.
Pubblicazione: (2025)

Randomized batch-sampling Kaczmarz methods for solving linear systems
di: Xie, Dong-Yue, et al.
Pubblicazione: (2025)

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

Compression of Currents and Varifolds
di: Paul, Allen, et al.
Pubblicazione: (2024)

Isovolumetric Energy Minimization for Ball-Shaped Volume-Preserving Parameterizations of 3-Manifolds
di: Liu, Shu-Yung, et al.
Pubblicazione: (2024)

Accurately recover global quasiperiodic systems by finite points
di: Jiang, Kai, et al.
Pubblicazione: (2023)

Stochastic trace estimation for parameter-dependent matrices applied to spectral density approximation
di: Matti, Fabio, et al.
Pubblicazione: (2025)

A discontinuous Galerkin plane wave neural network method for Helmholtz equation and Maxwell's equations
di: Yuan, Long, et al.
Pubblicazione: (2025)

Data-Driven Discovery of Sign-Indefinite Artificial Viscosity for Linear Convection -- A Space-Time Reconvolution Perspective
di: Neelan, Arun Govind
Pubblicazione: (2026)

Least Squares with Equality constraints Extreme Learning Machines for the resolution of PDEs
di: De Falco, Davide Elia, et al.
Pubblicazione: (2025)

Geometric Generalization of Neural Operators from Kernel Integral Perspective
di: Han, Mingyu, et al.
Pubblicazione: (2026)

A Neural Multigrid Solver for Helmholtz Equations with High Wavenumber and Heterogeneous Media
di: Cui, Chen, et al.
Pubblicazione: (2024)

Sampling Distributions as Regularization in Learned Inverse Problems
di: Babyale, Sandra R., et al.
Pubblicazione: (2026)

EGPT-PINN: Entropy-enhanced Generative Pre-Trained Physics Informed Neural Networks for parameterized nonlinear conservation laws
di: Ji, Yajie, et al.
Pubblicazione: (2025)

Prediction of discretization of online GMsFEM using deep learning for Richards equation
di: Spiridonov, Denis, et al.
Pubblicazione: (2024)

Discontinuous hybrid neural networks for the one-dimensional partial differential equations
di: Wang, Xiaoyu, et al.
Pubblicazione: (2025)

Neural enrichment finite element method: A hybrid framework for problems with strong oscillations or interface problems
di: Guo, Shihan, et al.
Pubblicazione: (2026)

Robust Blockwise Random Pivoting: Fast and Accurate Adaptive Interpolative Decomposition
di: Dong, Yijun, et al.
Pubblicazione: (2023)

Space-time parallel scaling of Parareal with a physics-informed Fourier Neural Operator coarse propagator applied to the Black-Scholes equation
di: Ibrahim, Abdul Qadir, et al.
Pubblicazione: (2024)

Subspace method based on neural networks for eigenvalue problems
di: Dai, Xiaoying, et al.
Pubblicazione: (2024)