English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Bilevel Optimization has witnessed notable progress recently with newemerging efficient algorithms and has been applied to many machine learningtasks such as data cleaning, few-shot learning, and neural architecture search.However, little attention has been paid to solve the bilevel problems underdistributed setting. Federated learning (FL) is an emerging paradigm whichsolves machine learning tasks over distributed-located data. FL problems arechallenging to solve due to the heterogeneity and communication bottleneck.However, it is unclear how these challenges will affect the convergence ofBilevel Optimization algorithms. In this paper, we study Federated BilevelOptimization problems. Specifically, we first propose the FedBiO, adeterministic gradient-based algorithm and we show it requires$O(\epsilon^{-2})$ number of iterations to reach an $\epsilon$-stationarypoint. Then we propose FedBiOAcc to accelerate FedBiO with the momentum-basedvariance-reduction technique under the stochastic scenario. We show FedBiOAcchas complexity of $O(\epsilon^{-1.5})$. Finally, we validate our proposedalgorithms via the important Fair Federated Learning task. More specifically,we define a bilevel-based group fair FL objective. Our algorithms show superiorperformances compared to other baselines in numerical experiments.

Local Stochastic Bilevel Optimization with Momentum-Based Variance Reduction