BriefGPT.xyz
May, 2024
从学习优化到学习优化算法
From Learning to Optimize to Learning Optimization Algorithms
HTML
PDF
Camille Castera, Peter Ochs
TL;DR
通过识别经典算法服从的关键原则并将其用于优化学习(L2O)中,我们提供了一个综合设计流程,以数据、架构和学习策略为考虑因素,从而实现经典优化与L2O之间的协同,形成了学习优化算法的理念。通过设计一种新的增强学习BFGS算法并提供数值实验证明其在多种测试环境中的适应性,我们展示了这些新原则的成功。
Abstract
Towards designing
learned optimization algorithms
that are usable beyond their training setting, we identify key principles that
classical algorithms
obey, but have up to now, not been used for
→