vix.ing · top · new · best · stats · spec

Principled Acceleration of Iterative Numerical Methods Using Machine Learning

2022/06/17 by Sohei Arisaka, Arisaka, Sohei, Qianxiao Li +1 · 2 citations
Environmental Science · Physics and Astronomy · #65M06 #68T99 #68U20 #FOS: Computer and information sciences #FOS: Mathematics #Groundwater flow and contamination studies #Machine Learning (cs.LG) #Model Reduction and Neural Networks #Numerical Analysis (math.NA)

paper · pdf · doi:10.48550/arxiv.2206.08594

openalex publication_date 2022/06/17 · openalex created_date 2022/06/22 · openalex updated_date 2026/07/28

Abstract

Iterative methods are ubiquitous in large-scale scientific computing applications, and a number of approaches based on meta-learning have been recently proposed to accelerate them. However, a systematic study of these approaches and how they differ from meta-learning is lacking. In this paper, we propose a framework to analyze such learning-based acceleration approaches, where one can immediately identify a departure from classical meta-learning. We show that this departure may lead to arbitrary deterioration of model performance. Based on our analysis, we introduce a novel training method for learning-based acceleration of iterative methods. Furthermore, we theoretically prove that the proposed method improves upon the existing methods, and demonstrate its significant advantage and versatility through various numerical applications.

Cited by

Related