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 sample complexity of learning the optimal arm formulti-task bandit problems. Arms consist of two components: one that is sharedacross tasks (that we call representation) and one that is task-specific (thatwe call predictor). The objective is to learn the optimal (representation,predictor)-pair for each task, under the assumption that the optimalrepresentation is common to all tasks. Within this framework, efficientlearning algorithms should transfer knowledge across tasks. We consider thebest-arm identification problem for a fixed confidence, where, in each round,the learner actively selects both a task, and an arm, and observes thecorresponding reward. We derive instance-specific sample complexity lowerbounds satisfied by any $(\delta_G,\delta_H)$-PAC algorithm (such an algorithmidentifies the best representation with probability at least $1-\delta_G$, andthe best predictor for a task with probability at least $1-\delta_H$). Wedevise an algorithm OSRL-SC whose sample complexity approaches the lower bound,and scales at most as $H(G\log(1/\delta_G)+ X\log(1/\delta_H))$, with $X,G,H$being, respectively, the number of tasks, representations and predictors. Bycomparison, this scaling is significantly better than the classical best-armidentification algorithm that scales as $HGX\log(1/\delta)$.

On the Sample Complexity of Representation Learning in Multi-task Bandits with Global and Local structure