Back to Search Start Over

Compositional ADAM: An Adaptive Compositional Solver

Authors :
Tutunov, Rasul
Li, Minne
Cowen-Rivers, Alexander I.
Wang, Jun
Bou-Ammar, Haitham
Publication Year :
2020

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 $\mathcal{O}(\delta^{-2.25})$ with $\delta$ 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.

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2002.03755
Document Type :
Working Paper