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

Deployed machine learning (ML) models often encounter new user data thatdiffers from their training data. Therefore, estimating how well a given modelmight perform on the new data is an important step toward reliable MLapplications. This is very challenging, however, as the data distribution canchange in flexible ways, and we may not have any labels on the new data, whichis often the case in monitoring settings. In this paper, we propose a newdistribution shift model, Sparse Joint Shift (SJS), which considers the jointshift of both labels and a few features. This unifies and generalizes severalexisting shift models including label shift and sparse covariate shift, whereonly marginal feature or label distribution shifts are considered. We describemathematical conditions under which SJS is identifiable. We further proposeSEES, an algorithmic framework to characterize the distribution shift under SJSand to estimate a model's performance on new data without any labels. Weconduct extensive experiments on several real-world datasets with various MLmodels. Across different datasets and distribution shifts, SEES achievessignificant (up to an order of magnitude) shift estimation error improvementsover existing approaches.

Estimating and Explaining Model Performance When Both Covariates and Labels Shift