Timezone: »

Provably Faster Algorithms for Bilevel Optimization
Junjie Yang · Kaiyi Ji · Yingbin Liang

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 $\mathcal{\widetilde O}(\epsilon^{-2})$ 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 $\mathcal{\widetilde O}(\epsilon^{-1.5})$, 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.

Author Information

Junjie Yang (Ohio State University)
Kaiyi Ji (The Ohio State University)
Yingbin Liang (The Ohio State University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors