Bilevel Optimization with a Lower-level Contraction: Optimal Sample Complexity without Warm-start
This addresses a bottleneck in meta-learning and equilibrium models where warm-start is ineffective, offering a simpler and more broadly applicable solution.
The paper tackles bilevel optimization problems without requiring warm-start procedures, achieving order-wise (near) optimal sample complexity of O(ε^{-2}) in stochastic and Õ(ε^{-1}) in deterministic settings.
We analyse a general class of bilevel problems, in which the upper-level problem consists in the minimization of a smooth objective function and the lower-level problem is to find the fixed point of a smooth contraction map. This type of problems include instances of meta-learning, equilibrium models, hyperparameter optimization and data poisoning adversarial attacks. Several recent works have proposed algorithms which warm-start the lower-level problem, i.e.~they use the previous lower-level approximate solution as a staring point for the lower-level solver. This warm-start procedure allows one to improve the sample complexity in both the stochastic and deterministic settings, achieving in some cases the order-wise optimal sample complexity. However, there are situations, e.g., meta learning and equilibrium models, in which the warm-start procedure is not well-suited or ineffective. In this work we show that without warm-start, it is still possible to achieve order-wise (near) optimal sample complexity. In particular, we propose a simple method which uses (stochastic) fixed point iterations at the lower-level and projected inexact gradient descent at the upper-level, that reaches an $ε$-stationary point using $O(ε^{-2})$ and $\tilde{O}(ε^{-1})$ samples for the stochastic and the deterministic setting, respectively. Finally, compared to methods using warm-start, our approach yields a simpler analysis that does not need to study the coupled interactions between the upper-level and lower-level iterates.