Provably Faster Algorithms for Bilevel Optimization

arXiv2106.04692MaRDI QIDQ6369799

Author name not available (Why is that?)

Publication date: 8 June 2021

Abstract: Bilevel optimization has been widely applied in many important machine learning applications such as hyperparameter optimization and meta-learning. Recently, several momentum-based algorithms have been proposed to solve bilevel optimization problems faster. However, those momentum-based algorithms do not achieve provably better computational complexity than $mathcalwidetildeO(epsilo{n}^{-2})$ of the SGD-based algorithm. In this paper, we propose two new algorithms for bilevel optimization, where the first algorithm adopts momentum-based recursive iterations, and the second algorithm adopts recursive gradient estimations in nested loops to decrease the variance. We show that both algorithms achieve the complexity of $mathcalwidetildeO(epsilo{n}^{-1.5})$, which outperforms all existing algorithms by the order of magnitude. Our experiments validate our theoretical results and demonstrate the superior empirical performance of our algorithms in hyperparameter applications.

Has companion code repository: https://github.com/JunjieYang97/MRVRBO

This page was built for publication: Provably Faster Algorithms for Bilevel Optimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6369799)