A Conditional Gradient-based Method for Simple Bilevel Optimization with Convex Lower-level Problem

TL;DR

This paper introduces a new conditional gradient-based method for simple bilevel optimization problems with convex lower-level constraints, achieving improved convergence rates over existing methods.

Contribution

The paper proposes a novel bilevel optimization algorithm that approximates the lower-level solution set with a cutting plane and uses a conditional gradient update, providing the best-known iteration complexity.

Findings

Requires ${ m O}(rac{1}{\e_f}, rac{1}{\e_g})$ iterations for convex upper-level objectives.

Requires ${ m O}(rac{1}{\e_f^2}, rac{1}{\e_f \e_g})$ iterations for non-convex upper-level objectives.

Achieves stronger convergence guarantees under H"olderian error bound assumptions.

Abstract

In this paper, we study a class of bilevel optimization problems, also known as simple bilevel optimization, where we minimize a smooth objective function over the optimal solution set of another convex constrained optimization problem. Several iterative methods have been developed for tackling this class of problems. Alas, their convergence guarantees are either asymptotic for the upper-level objective, or the convergence rates are slow and sub-optimal. To address this issue, in this paper, we introduce a novel bilevel optimization method that locally approximates the solution set of the lower-level problem via a cutting plane, and then runs a conditional gradient update to decrease the upper-level objective. When the upper-level objective is convex, we show that our method requires ${\mathcal{O}}(\max\{1/\epsilon_f,1/\epsilon_g\})$ iterations to find a solution that is $\epsilon_f$-optimal for the upper-level objective and $\epsilon_g$-optimal for the lower-level objective. Moreover, when the upper-level objective is non-convex, our method requires ${\mathcal{O}}(\max\{1/\epsilon_f^2,1/(\epsilon_f\epsilon_g)\})$ iterations to find an $(\epsilon_f,\epsilon_g)$-optimal solution. We also prove stronger convergence guarantees under the H\"olderian error bound assumption on the lower-level problem. To the best of our knowledge, our method achieves the best-known iteration complexity for the considered class of bilevel problems.