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

We propose Byzantine-robust federated learning protocols with nearly optimalstatistical rates. In contrast to prior work, our proposed protocols improvethe dimension dependence and achieve a tight statistical rate in terms of allthe parameters for strongly convex losses. We benchmark against competingprotocols and show the empirical superiority of the proposed protocols.Finally, we remark that our protocols with bucketing can be naturally combinedwith privacy-guaranteeing procedures to introduce security against asemi-honest server. The code for evaluation is provided inhttps://github.com/wanglun1996/secure-robust-federated-learning.

Byzantine-Robust Federated Learning with Optimal Statistical Rates and Privacy Guarantees