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 introduce a new model for multivariate probabilistic time seriesprediction, designed to flexibly address a range of tasks includingforecasting, interpolation, and their combinations. Building on copula theory,we propose a simplified objective for the recently-introduced transformer-basedattentional copulas (TACTiS), wherein the number of distributional parametersnow scales linearly with the number of variables instead of factorially. Thenew objective requires the introduction of a training curriculum, which goeshand-in-hand with necessary changes to the original architecture. We show thatthe resulting model has significantly better training dynamics and achievesstate-of-the-art performance across diverse real-world forecasting tasks, whilemaintaining the flexibility of prior work, such as seamless handling ofunaligned and unevenly-sampled time series.

TACTiS-2: Better, Faster, Simpler Attentional Copulas for Multivariate Time Series