When Does MAML Objective Have Benign Landscape?
Machine Learning
2020-12-14 v2 Optimization and Control
Machine Learning
Abstract
The paper studies the complexity 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 are curious to know when, if at all, the benign 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.
Cite
@article{arxiv.2006.00453,
title = {When Does MAML Objective Have Benign Landscape?},
author = {Igor Molybog and Javad Lavaei},
journal= {arXiv preprint arXiv:2006.00453},
year = {2020}
}
Comments
12 pages, 3 figures