Saved in:
Bibliographic Details
Main Authors: Cho, Younghyun, Demmel, James W., Dereziński, Michał, Li, Haoyun, Luo, Hengrui, Mahoney, Michael W., Murray, Riley J.
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2308.15720
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910779100364800
author Cho, Younghyun
Demmel, James W.
Dereziński, Michał
Li, Haoyun
Luo, Hengrui
Mahoney, Michael W.
Murray, Riley J.
author_facet Cho, Younghyun
Demmel, James W.
Dereziński, Michał
Li, Haoyun
Luo, Hengrui
Mahoney, Michael W.
Murray, Riley J.
contents Algorithms from Randomized Numerical Linear Algebra (RandNLA) are known to be effective in handling high-dimensional computational problems, providing high-quality empirical performance as well as strong probabilistic guarantees. However, their practical application is complicated by the fact that the user needs to set various algorithm-specific tuning parameters which are different than those used in traditional NLA. This paper demonstrates how a surrogate-based autotuning approach can be used to address fundamental problems of parameter selection in RandNLA algorithms. In particular, we provide a detailed investigation of surrogate-based autotuning for sketch-and-precondition (SAP) based randomized least squares methods, which have been one of the great success stories in modern RandNLA. Empirical results show that our surrogate-based autotuning approach can achieve near-optimal performance with much less tuning cost than a random search (up to about 4x fewer trials of different parameter configurations). Moreover, while our experiments focus on least squares, our results demonstrate a general-purpose autotuning pipeline applicable to any kind of RandNLA algorithm.
format Preprint
id arxiv_https___arxiv_org_abs_2308_15720
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Surrogate-based Autotuning for Randomized Sketching Algorithms in Regression Problems
Cho, Younghyun
Demmel, James W.
Dereziński, Michał
Li, Haoyun
Luo, Hengrui
Mahoney, Michael W.
Murray, Riley J.
Machine Learning
Artificial Intelligence
68W20, 65F20, 65Y20
Algorithms from Randomized Numerical Linear Algebra (RandNLA) are known to be effective in handling high-dimensional computational problems, providing high-quality empirical performance as well as strong probabilistic guarantees. However, their practical application is complicated by the fact that the user needs to set various algorithm-specific tuning parameters which are different than those used in traditional NLA. This paper demonstrates how a surrogate-based autotuning approach can be used to address fundamental problems of parameter selection in RandNLA algorithms. In particular, we provide a detailed investigation of surrogate-based autotuning for sketch-and-precondition (SAP) based randomized least squares methods, which have been one of the great success stories in modern RandNLA. Empirical results show that our surrogate-based autotuning approach can achieve near-optimal performance with much less tuning cost than a random search (up to about 4x fewer trials of different parameter configurations). Moreover, while our experiments focus on least squares, our results demonstrate a general-purpose autotuning pipeline applicable to any kind of RandNLA algorithm.
title Surrogate-based Autotuning for Randomized Sketching Algorithms in Regression Problems
topic Machine Learning
Artificial Intelligence
68W20, 65F20, 65Y20
url https://arxiv.org/abs/2308.15720