Asynchronous Distributed Bilevel Optimization

arXiv2212.10048MaRDI QIDQ6421069FDOQ6421069

Authors: Yang Jiao, Kai Yang, Tiancheng Wu, Dongjin Song, Chengtao Jian 

Publication date: 20 December 2022

Abstract: Bilevel optimization plays an essential role in many machine learning tasks, ranging from hyperparameter optimization to meta-learning. Existing studies on bilevel optimization, however, focus on either centralized or synchronous distributed setting. The centralized bilevel optimization approaches require collecting massive amount of data to a single server, which inevitably incur significant communication expenses and may give rise to data privacy risks. Synchronous distributed bilevel optimization algorithms, on the other hand, often face the straggler problem and will immediately stop working if a few workers fail to respond. As a remedy, we propose Asynchronous Distributed Bilevel Optimization (ADBO) algorithm. The proposed ADBO can tackle bilevel optimization problems with both nonconvex upper-level and lower-level objective functions, and its convergence is theoretically guaranteed. Furthermore, it is revealed through theoretic analysis that the iteration complexity of ADBO to obtain the $epsilon$-stationary point is upper bounded by $mathcalO(frac1epsilo{n}^2)$. Thorough empirical studies on public datasets have been conducted to elucidate the effectiveness and efficiency of the proposed ADBO.

Has companion code repository: https://github.com/iclr23submission6251/adbo

This page was built for publication: Asynchronous Distributed Bilevel Optimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6421069)