BOME! Bilevel Optimization Made Easy: A Simple First-Order Approach

Author name not available (Why is that?)

Publication date: 18 September 2022

Abstract: Bilevel optimization (BO) is useful for solving a variety of important machine learning problems including but not limited to hyperparameter optimization, meta-learning, continual learning, and reinforcement learning. Conventional BO methods need to differentiate through the low-level optimization process with implicit differentiation, which requires expensive calculations related to the Hessian matrix. There has been a recent quest for first-order methods for BO, but the methods proposed to date tend to be complicated and impractical for large-scale deep learning applications. In this work, we propose a simple first-order BO algorithm that depends only on first-order gradient information, requires no implicit differentiation, and is practical and efficient for large-scale non-convex functions in deep learning. We provide non-asymptotic convergence analysis of the proposed method to stationary points for non-convex objectives and present empirical results that show its superior practical performance.

Has companion code repository: https://github.com/cranial-xix/bome

This page was built for publication: BOME! Bilevel Optimization Made Easy: A Simple First-Order Approach

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6411149)