Beyond backpropagation: bilevel optimization through implicit differentiation and equilibrium propagation

arXiv (Cornell University)(2022)

引用 0|浏览2
暂无评分
摘要
This paper reviews gradient-based techniques to solve bilevel optimization problems. Bilevel optimization is a general way to frame the learning of systems that are implicitly defined through a quantity that they minimize. This characterization can be applied to neural networks, optimizers, algorithmic solvers and even physical systems, and allows for greater modeling flexibility compared to an explicit definition of such systems. Here we focus on gradient-based approaches that solve such problems. We distinguish them in two categories: those rooted in implicit differentiation, and those that leverage the equilibrium propagation theorem. We present the mathematical foundations that are behind such methods, introduce the gradient-estimation algorithms in detail and compare the competitive advantages of the different approaches.
更多
查看译文
关键词
backpropagation,optimization,backpropagation,differentiation,equilibrium
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络