A Multi-level procedure for enhancing accuracy of machine learning algorithms
METADATA ONLY
Loading...
Author / Producer
Date
2019-09
Publication Type
Report
ETH Bibliography
yes
Citations
Altmetric
METADATA ONLY
Data
Rights / License
Abstract
We propose a multi-level method to increase the accuracy of machine learning algorithms for approximating observables in scientific computing, particularly those that arise in systems modeled by differential equations. The algorithm relies on judiciously combining a large number of computationally cheap training data on coarse resolutions with a few expensive training samples on fine grid resolutions. Theoretical arguments for lowering the generalization error, based on reducing the variance of the underlying maps, are provided and numerical evidence, indicating significant gains over underlying single-level machine learning algorithms, are presented. Moreover, we also apply the multi-level algorithm in the context of forward uncertainty quantification and observe a considerable speed-up over competing algorithms.
Permanent link
Publication status
published
Editor
Book title
Journal / series
Volume
2019-54
Pages / Article No.
Publisher
Seminar for Applied Mathematics, ETH Zurich
Event
Edition / version
Methods
Software
Geographic location
Date collected
Date created
Subject
machine learning; Multi-level Monte Carlo; multi-level; deep learning; uncertainty quantifications
Organisational unit
03851 - Mishra, Siddhartha / Mishra, Siddhartha
Notes
Funding
770880 - Computation and analysis of statistical solutions of fluid flow (EC)
Related publications and datasets
Is previous version of: