Compositional ADAM: An Adaptive Compositional Solver
Machine Learning
2020-04-27 v2 Optimization and Control
Machine Learning
Abstract
In this paper, we present C-ADAM, the first adaptive solver for compositional problems involving a non-linear functional nesting of expected values. We proof that C-ADAM converges to a stationary point in with being a precision parameter. Moreover, we demonstrate the importance of our results by bridging, for the first time, model-agnostic meta-learning (MAML) and compositional optimisation showing fastest known rates for deep network adaptation to-date. Finally, we validate our findings in a set of experiments from portfolio optimisation and meta-learning. Our results manifest significant sample complexity reductions compared to both standard and compositional solvers.
Keywords
Cite
@article{arxiv.2002.03755,
title = {Compositional ADAM: An Adaptive Compositional Solver},
author = {Rasul Tutunov and Minne Li and Alexander I. Cowen-Rivers and Jun Wang and Haitham Bou-Ammar},
journal= {arXiv preprint arXiv:2002.03755},
year = {2020}
}