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

Real-world applications of contextual bandits often exhibit non-stationaritydue to seasonality, serendipity, and evolving social trends. While a number ofnon-stationary contextual bandit learning algorithms have been proposed in theliterature, they excessively explore due to a lack of prioritization forinformation of enduring value, or are designed in ways that do not scale inmodern applications with high-dimensional user-specific features and largeaction set, or both. In this paper, we introduce a novel non-stationarycontextual bandit algorithm that addresses these concerns. It combines ascalable, deep-neural-network-based architecture with a carefully designedexploration mechanism that strategically prioritizes collecting informationwith the most lasting value in a non-stationary environment. Through empiricalevaluations on two real-world recommendation datasets, which exhibit pronouncednon-stationarity, we demonstrate that our approach significantly outperformsthe state-of-the-art baselines.

Non-Stationary Contextual Bandit Learning via Neural Predictive Ensemble Sampling