Local Stochastic Bilevel Optimization with Momentum-Based Variance Reduction
This work addresses federated bilevel optimization, a novel combination of two challenging areas, but it is incremental as it adapts existing techniques to a new distributed setting.
The authors tackled federated bilevel optimization by proposing FedBiO and its accelerated variant FedBiOAcc, achieving complexities of O(ε^{-2}) and O(ε^{-1.5}) for reaching ε-stationary points, respectively, and demonstrating superior performance in fair federated learning tasks.
Bilevel Optimization has witnessed notable progress recently with new emerging efficient algorithms and has been applied to many machine learning tasks such as data cleaning, few-shot learning, and neural architecture search. However, little attention has been paid to solve the bilevel problems under distributed setting. Federated learning (FL) is an emerging paradigm which solves machine learning tasks over distributed-located data. FL problems are challenging to solve due to the heterogeneity and communication bottleneck. However, it is unclear how these challenges will affect the convergence of Bilevel Optimization algorithms. In this paper, we study Federated Bilevel Optimization problems. Specifically, we first propose the FedBiO, a deterministic gradient-based algorithm and we show it requires $O(ε^{-2})$ number of iterations to reach an $ε$-stationary point. Then we propose FedBiOAcc to accelerate FedBiO with the momentum-based variance-reduction technique under the stochastic scenario. We show FedBiOAcc has complexity of $O(ε^{-1.5})$. Finally, we validate our proposed algorithms via the important Fair Federated Learning task. More specifically, we define a bilevel-based group fair FL objective. Our algorithms show superior performances compared to other baselines in numerical experiments.