When Does MAML Objective Have Benign Landscape?
2021 IEEE Conference on Control Technology and Applications (CCTA)2021pp. 220–227
Citations Over Time
Abstract
The paper studies the landscape of the optimization problem behind the Model-Agnostic Meta-Learning (MAML) algorithm. The goal of the study is to determine the global convergence of MAML on sequential decision-making tasks possessing a common structure. We investigate in what scenarios the benign optimization landscape of the underlying tasks results in a benign landscape of the corresponding MAML objective. For illustration, we analyze the landscape of the MAML objective on LQR tasks to determine what types of similarities in their structures enable the algorithm to converge to the globally optimal solution.