Imagen de Portada

Randomized Matrix Sketching for Neural Network Training and Gradient Monitoring

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Antil, Harbir, Verma, Deepanshu
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning 68T07, 65F55, 65K10, 68W20
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Sequential Least-Squares Estimators with Fast Randomized Sketching for Linear Statistical Models
por: Chen, Guan-Yu, et al.
Publicado: (2025)

Robust, randomized preconditioning for kernel ridge regression
por: Díaz, Mateo, et al.
Publicado: (2023)

Model Parallel Training and Transfer Learning for Convolutional Neural Networks by Domain Decomposition
por: Klawonn, Axel, et al.
Publicado: (2024)

Randomized flexible Krylov methods for $\ell_p$ regularization
por: Landman, Malena Sabaté, et al.
Publicado: (2025)

Improving Sketching Algorithms for Low-Rank Matrix Approximation via Sketch-Power Iterations
por: Chang, Chao, et al.
Publicado: (2026)

Surrogate-based Autotuning for Randomized Sketching Algorithms in Regression Problems
por: Cho, Younghyun, et al.
Publicado: (2023)

Randomized coupled decompositions
por: Begovic, Erna, et al.
Publicado: (2024)

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

A Paired Autoencoder Framework for Inverse Problems via Bayes Risk Minimization
por: Hart, Emma, et al.
Publicado: (2025)

Row-aware Randomized SVD with applications
por: Palitta, Davide, et al.
Publicado: (2024)

Fast and forward stable randomized algorithms for linear least-squares problems
por: Epperly, Ethan N.
Publicado: (2023)

Fast randomized least-squares solvers can be just as accurate and stable as classical direct solvers
por: Epperly, Ethan N., et al.
Publicado: (2024)

Distributed Hybrid Sketching for $\ell_2$-Embeddings
por: Charalambides, Neophytos, et al.
Publicado: (2024)

Efficient Sketching-Based Summation of Tucker Tensors
por: Smith, Rudi, et al.
Publicado: (2026)

A Domain Decomposition-Based CNN-DNN Architecture for Model Parallel Training Applied to Image Recognition Problems
por: Klawonn, Axel, et al.
Publicado: (2023)

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

Relaxed Greedy Randomized Kaczmarz with Signal Averaging for Solving Doubly-Noisy Linear Systems
por: Zhang, Lu, et al.
Publicado: (2026)

Domain-decomposed image classification algorithms using linear discriminant analysis and convolutional neural networks
por: Klawonn, Axel, et al.
Publicado: (2024)

Approximation and Gradient Descent Training with Neural Networks
por: Welper, G.
Publicado: (2024)

Sharp analysis of sketched least squares and randomized low-rank approximation
por: Epperly, Ethan N., et al.
Publicado: (2026)

Randomized Large-Scale Quaternion Matrix Approximation: Practical Rangefinders and One-Pass Algorithm
por: Chang, Chao, et al.
Publicado: (2024)

Linear-Scaling Tensor Train Sketching
por: Cazeaux, Paul, et al.
Publicado: (2026)

Deep Unfolding Network for Nonlinear Multi-Frequency Electrical Impedance Tomography
por: Alberti, Giovanni S., et al.
Publicado: (2025)

Adaptive randomized pivoting for column subset selection, DEIM, and low-rank approximation
por: Cortinovis, Alice, et al.
Publicado: (2024)

Convergence of Momentum-Based Optimization Algorithms with Time-Varying Parameters
por: Vidyasagar, Mathukumalli
Publicado: (2025)

Subspace-constrained randomized coordinate descent for linear systems with good low-rank matrix approximations
por: Lok, Jackie, et al.
Publicado: (2025)

Beyond Low Rank: Fast Low-Rank + Diagonal Decomposition with a Spectral Approach
por: Yeon, Kingsley, et al.
Publicado: (2025)

Parallelization Strategies for the Randomized Kaczmarz Algorithm on Large-Scale Dense Systems
por: Ferreira, Inês, et al.
Publicado: (2024)

Sketched and Truncated Polynomial Krylov Subspace Methods: Matrix Sylvester Equations
por: Palitta, Davide, et al.
Publicado: (2023)

Randomized sketched TT-GMRES for linear systems with tensor structure
por: Bucci, Alberto, et al.
Publicado: (2024)

Make the most of what you have: Resource-efficient randomized algorithms for matrix computations
por: Epperly, Ethan N.
Publicado: (2025)

Parallel Energy-Minimization Prolongation for Algebraic Multigrid
por: Janna, Carlo, et al.
Publicado: (2022)

Efficient error and variance estimation for randomized matrix computations
por: Epperly, Ethan N., et al.
Publicado: (2022)

Multilevel Training for Kolmogorov Arnold Networks
por: Southworth, Ben S., et al.
Publicado: (2026)

A Neural-Operator Preconditioned Newton Method for Accelerated Nonlinear Solvers
por: Lee, Youngkyu, et al.
Publicado: (2025)

Parallel-in-time Multilevel Krylov Methods: A Prototype
por: Erlangga, Yogi A.
Publicado: (2023)

Randomized Nyström approximation of non-negative self-adjoint operators
por: Persson, David, et al.
Publicado: (2024)

Optimal Sensor Placement in Gaussian Processes via Column Subset Selection
por: Chen, Jessie, et al.
Publicado: (2026)

Gradient Coding with Iterative Block Leverage Score Sampling
por: Charalambides, Neophytos, et al.
Publicado: (2023)

Quasi-optimal hierarchically semi-separable matrix approximation
por: Amsel, Noah, et al.
Publicado: (2025)