A Multi-level procedure for enhancing accuracy of machine learning algorithms

09/20/2019
by   Kjetil O. Lye, et al.
0

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.

READ FULL TEXT
research
02/14/2021

Multi-Level Fine-Tuning: Closing Generalization Gaps in Approximation of Solution Maps under a Limited Budget for Training Data

In scientific machine learning, regression networks have been recently a...
research
05/26/2020

Enhancing accuracy of deep learning algorithms by training with low-discrepancy sequences

We propose a deep supervised learning algorithm based on low-discrepancy...
research
04/27/2020

Multi-level neural networks for PDEs with uncertain parameters

A novel multi-level method for partial differential equations with uncer...
research
05/23/2023

A Block-Coordinate Approach of Multi-level Optimization with an Application to Physics-Informed Neural Networks

Multi-level methods are widely used for the solution of large-scale prob...
research
02/06/2023

Multi-fidelity microstructure-induced uncertainty quantification by advanced Monte Carlo methods

Quantifying uncertainty associated with the microstructure variation of ...
research
10/26/2022

Multi-level Data Representation For Training Deep Helmholtz Machines

A vast majority of the current research in the field of Machine Learning...
research
05/03/2019

Matlab vs. OpenCV: A Comparative Study of Different Machine Learning Algorithms

Scientific Computing relies on executing computer algorithms coded in so...

Please sign up or login with your details

Forgot password? Click here to reset