BriefGPT.xyz
Jun, 2022
利用辅助信息进行优化
Optimization with access to auxiliary information
HTML
PDF
El Mahdi Chayti, Sai Praneeth Karimireddy
TL;DR
探讨了最小化梯度难以计算或有限可用性的目标函数$f(x)$的基本优化问题，给定某些较为廉价或更可用的辅助边函数$h(x)$来最小化。提出了两种新的通用算法，证明只需在目标和边信息之间进行Hessian相似性的假设即可从该框架中受益。
Abstract
We investigate the fundamental
optimization
question of minimizing a target function $f(x)$ whose
gradients
are expensive to compute or have limited availability, given access to some auxiliary side function $h(x
→