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 machine learning, the domain adaptation problem arrives when the test(target) and the train (source) data are generated from differentdistributions. A key applied issue is thus the design of algorithms able togeneralize on a new distribution, for which we have no label information. Wefocus on learning classification models defined as a weighted majority voteover a set of real-val ued functions. In this context, Germain et al. (2013)have shown that a measure of disagreement between these functions is crucial tocontrol. The core of this measure is a theoretical bound--the C-bound (Lacasseet al., 2007)--which involves the disagreement and leads to a well performingmajority vote learning algorithm in usual non-adaptative supervised setting:MinCq. In this work, we propose a framework to extend MinCq to a domainadaptation scenario. This procedure takes advantage of the recent perturbedvariation divergence between distributions proposed by Harel and Mannor (2012).Justified by a theoretical bound on the target risk of the vote, we provide toMinCq a target sample labeled thanks to a perturbed variation-basedself-labeling focused on the regions where the source and target marginalsappear similar. We also study the influence of our self-labeling, from which wededuce an original process for tuning the hyperparameters. Finally, ourframework called PV-MinCq shows very promising results on a rotation andtranslation synthetic problem.

Domain adaptation of weighted majority votes via perturbed variation-based self-labeling