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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

We address the relatively unexplored problem of hyper-parameter optimization(HPO) for federated learning (FL-HPO). We introduce Federated Loss SuRfaceAggregation (FLoRA), a general FL-HPO solution framework that can address usecases of tabular data and any Machine Learning (ML) model including gradientboosting training algorithms and therefore further expands the scope of FL-HPO.FLoRA enables single-shot FL-HPO: identifying a single set of goodhyper-parameters that are subsequently used in a single FL training. Thus, itenables FL-HPO solutions with minimal additional communication overheadcompared to FL training without HPO. We theoretically characterize theoptimality gap of FL-HPO, which explicitly accounts for the heterogeneousnon-IID nature of the parties' local data distributions, a dominantcharacteristic of FL systems. Our empirical evaluation of FLoRA for multiple MLalgorithms on seven OpenML datasets demonstrates significant model accuracyimprovements over the considered baseline, and robustness to increasing numberof parties involved in FL-HPO training.

Single-shot Hyper-parameter Optimization for Federated Learning: A General Algorithm & Analysis