BriefGPT.xyz
Mar, 2024
使用非线性系统理论学习带有收敛保证的优化方法
Learning to optimize with convergence guarantees using nonlinear system theory
HTML
PDF
Andrea Martin, Luca Furieri
TL;DR
我们提出了一个利用非线性系统理论填补演进中算法收敛性和鲁棒性分析的理论框架,可以自动化地优化学习到的算法,保证其设计上的收敛性。
Abstract
The increasing reliance on
numerical methods
for controlling dynamical systems and training
machine learning models
underscores the need to devise algorithms that dependably and efficiently navigate complex
→