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

In supervised learning, we fit a single statistical model to a given dataset, assuming that the data is associated with a singular task, which yieldswell-tuned models for specific use, but does not adapt well to new contexts. Bycontrast, in meta-learning, the data is associated with numerous tasks, and weseek a model that may perform well on all tasks simultaneously, in pursuit ofgreater generalization. One challenge in meta-learning is how to exploitrelationships between tasks and classes, which is overlooked by commonly usedrandom or cyclic passes through data. In this work, we propose activelyselecting samples on which to train by discerning covariates inside and betweenmeta-training sets. Specifically, we cast the problem of selecting a samplefrom a number of meta-training sets as either a multi-armed bandit or a MarkovDecision Process (MDP), depending on how one encapsulates correlation acrosstasks. We develop scheduling schemes based on Upper Confidence Bound (UCB),Gittins Index and tabular Markov Decision Problems (MDPs) solved with linearprogramming, where the reward is the scaled statistical accuracy to ensure itis a time-invariant function of state and action. Across a variety ofexperimental contexts, we observe significant reductions in sample complexityof active selection scheme relative to cyclic or i.i.d. sampling, demonstratingthe merit of exploiting covariates in practice.

A Markov Decision Process Approach to Active Meta Learning