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 investigate the sparse linear contextual bandit problem where theparameter $\theta$ is sparse. To relieve the sampling inefficiency, we utilizethe "perturbed adversary" where the context is generated adversarilly but withsmall random non-adaptive perturbations. We prove that the simple online Lassosupports sparse linear contextual bandit with regret bound$\mathcal{O}(\sqrt{kT\log d})$ even when $d \gg T$ where $k$ and $d$ are thenumber of effective and ambient dimension, respectively. Compared to the recentwork from Sivakumar et al. (2020), our analysis does not rely on theprecondition processing, adaptive perturbation (the adaptive perturbationviolates the i.i.d perturbation setting) or truncation on the error set.Moreover, the special structures in our results explicitly characterize how theperturbation affects exploration length, guide the design of perturbationtogether with the fundamental performance limit of perturbation method.Numerical experiments are provided to complement the theoretical analysis.

A Smoothed Analysis of Online Lasso for the Sparse Linear Contextual Bandit Problem