首页|Optimization of Random Feature Method in the High-Precision Regime
Optimization of Random Feature Method in the High-Precision Regime
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
万方数据
Machine learning has been widely used for solving partial differential equations(PDEs)in recent years,among which the random feature method(RFM)exhibits spectral accuracy and can compete with traditional solvers in terms of both accuracy and efficiency.Potentially,the optimization problem in the RFM is more difficult to solve than those that arise in traditional methods.Unlike the broader machine-learning research,which frequently targets tasks within the low-precision regime,our study focuses on the high-precision regime crucial for solving PDEs.In this work,we study this problem from the following aspects:(i)we analyze the coefficient matrix that arises in the RFM by studying the distribution of singular values;(ii)we investigate whether the continuous training causes the overfitting issue;(iii)we test direct and iterative methods as well as randomized methods for solving the optimization problem.Based on these results,we find that direct methods are superior to other methods if memory is not an issue,while iterative methods typically have low accuracy and can be improved by preconditioning to some extent.
Random feature method(RFM)Partial differential equation(PDE)Least-squares problemDirect method Iterative method
Jingrun Chen、Weinan E、Yifei Sun
展开 >
School of Mathematical Sciences and Suzhou Institute for Advanced Research,Suzhou 215006 Jiangsu,China
University of Science and Technology of China,Hefei 230026,Anhui,China
Center for Machine Learning Research and School of Mathematical Sciences,Peking University,Beijing 100871,China
AI for Science Institute,Beijing 100084,China
School of Mathematical Sciences,Soochow University,Suzhou 215006,Jiangsu,China
展开 >
NSFC Major Research Plan-Interpretable and Generalpurpose Nextgeneration Artificial Intelligence
NETL
NSTL
万方数据
