• Classified by Topic • Classified by Publication Type • Sorted by Date • Sorted by First Author Last Name • Classified by Funding Source •
BOME! Bilevel Optimization Made Easy: A Simple First-Order Approach.
Bo
Liu, Mao Ye, Stephen Wright, Peter Stone, and Qiang Liu.
In Conference
on Neural Information Processing Systems, 2022, December 2022.
[PDF]4.2MB [slides.pdf]1.6MB [poster.pdf]885.6kB
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.
@InProceedings{NeurIPS2022-Liu,
author = {Bo Liu and Mao Ye and Stephen Wright and Peter Stone and Qiang Liu},
title = {BOME! Bilevel Optimization Made Easy: A Simple First-Order Approach},
booktitle = {Conference on Neural Information Processing Systems, 2022},
location = {New Orleans, LA},
month = {December},
year = {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.
},
}
Generated by bib2html.pl (written by Patrick Riley ) on Wed Apr 17, 2024 18:42:51