Training very large scale nonlinear SVMs using alternating direction method of multipliers coupled with the hierarchically semi-separable kernel approximations

DOI10.1016/j.ejco.2022.100046zbMath1530.68208arXiv2108.04167OpenAlexW3190714972MaRDI QIDQ6114955

Stefano Cipolla, Jacek Gondzio

Publication date: 12 July 2023

Published in: EURO Journal on Computational Optimization (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2108.04167

zbMATH Keywords

support vector machinesalternating direction method of multipliershierarchically semi-separable kernel approximations

Mathematics Subject Classification ID

Applications of mathematical programming (90C90) Learning and adaptive systems in artificial intelligence (68T05)

Related Items (1)

HODLR2D: A New Class of Hierarchical Matrices

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Finding structure with randomness: Probabilistic algorithms for constructing approximate matrix decompositions
• A fast adaptive solver for hierarchically semiseparable representations
• Kernel methods in machine learning
• Support-vector networks
• Parallel Algorithms for Nearest Neighbor Search Problems in High Dimensions
• Superfast and Stable Structured Solvers for Toeplitz Least Squares via Randomized Sampling
• Randomized algorithms for the low-rank approximation of matrices
• Randomized Algorithms for Matrices and Data
• 10.1162/15324430260185619
• A Fast Randomized Algorithm for Computing a Hierarchically Semiseparable Representation of a Matrix
• Faster Kernel Ridge Regression Using Sketching and Preconditioning
• Low-Rank Updates and a Divide-And-Conquer Method for Linear Matrix Equations
• hm-toolbox: MATLAB Software for HODLR and HSS Matrices
• On the Efficiency of Random Permutation for ADMM and Coordinate Descent
• Block Basis Factorization for Scalable Kernel Evaluation
• ASKIT: Approximate Skeletonization Kernel-Independent Treecode in High Dimensions
• A Distributed-Memory Package for Dense Hierarchically Semi-Separable Matrix Computations Using Randomization
• A Fast $ULV$ Decomposition Solver for Hierarchically Semiseparable Representations

This page was built for publication: Training very large scale nonlinear SVMs using alternating direction method of multipliers coupled with the hierarchically semi-separable kernel approximations