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 consider the non-stationary multi-armed bandit (MAB) framework and proposea Kolmogorov-Smirnov (KS) test based Thompson Sampling (TS) algorithm namedTS-KS, that actively detects change points and resets the TS parameters once achange is detected. In particular, for the two-armed bandit case, we derivebounds on the number of samples of the reward distribution to detect the changeonce it occurs. Consequently, we show that the proposed algorithm hassub-linear regret. Contrary to existing works, our algorithm is able to detecta change when the underlying reward distribution changes even though the meanreward remains the same. Finally, to test the efficacy of the proposedalgorithm, we employ it in two case-studies: i) task-offloading scenario inwireless edge-computing, and ii) portfolio optimization. Our results show thatthe proposed TS-KS algorithm outperforms not only the static TS algorithm butalso it performs better than other bandit algorithms designed fornon-stationary environments. Moreover, the performance of TS-KS is at par withthe state-of-the-art forecasting algorithms such as Facebook-PROPHET and ARIMA.

Kolmogorov-Smirnov Test-Based Actively-Adaptive Thompson Sampling for Non-Stationary Bandits