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

Early-exit neural networks (EENNs) facilitate adaptive inference by producingpredictions at multiple stages of the forward pass. In safety-criticalapplications, these predictions are only meaningful when complemented withreliable uncertainty estimates. Yet, due to their sequential structure, anEENN's uncertainty estimates should also be consistent: labels that are deemedimprobable at one exit should not reappear within the confidence interval / setof later exits. We show that standard uncertainty quantification techniques,like Bayesian methods or conformal prediction, can lead to inconsistency acrossexits. We address this problem by applying anytime-valid confidence sequences(AVCSs) to the exits of EENNs. By design, AVCSs maintain consistency acrossexits. We examine the theoretical and practical challenges of applying AVCSs toEENNs and empirically validate our approach on both regression andclassification tasks.

Anytime-Valid Confidence Sequences for Consistent Uncertainty Estimation in Early-Exit Neural Networks