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

Federated bilevel optimization (FBO) has shown great potential recently inmachine learning and edge computing due to the emerging nested optimizationstructure in meta-learning, fine-tuning, hyperparameter tuning, etc. However,existing FBO algorithms often involve complicated computations and requiremultiple sub-loops per iteration, each of which contains a number ofcommunication rounds. In this paper, we propose a simple and flexible FBOframework named SimFBO, which is easy to implement without sub-loops, andincludes a generalized server-side aggregation and update for improvingcommunication efficiency. We further propose System-level heterogeneity robustFBO (ShroFBO) as a variant of SimFBO with stronger resilience to heterogeneouslocal computation. We show that SimFBO and ShroFBO provably achieve a linearconvergence speedup with partial client participation and client samplingwithout replacement, as well as improved sample and communication complexities.Experiments demonstrate the effectiveness of the proposed methods over existingFBO algorithms.

SimFBO: Towards Simple, Flexible and Communication-efficient Federated Bilevel Learning