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

In this paper, we provide two main contributions in PAC-Bayesian theory fordomain adaptation where the objective is to learn, from a source distribution,a well-performing majority vote on a different target distribution. On the onehand, we propose an improvement of the previous approach proposed by Germain etal. (2013), that relies on a novel distribution pseudodistance based on adisagreement averaging, allowing us to derive a new tighter PAC-Bayesian domainadaptation bound for the stochastic Gibbs classifier. We specialize it tolinear classifiers, and design a learning algorithm which shows interestingresults on a synthetic problem and on a popular sentiment annotation task. Onthe other hand, we generalize these results to multisource domain adaptationallowing us to take into account different source domains. This study opens thedoor to tackle domain adaptation tasks by making use of all the PAC-Bayesiantools.

PAC-Bayesian Theorems for Domain Adaptation with Specialization to Linear Classifiers