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

Classifiers can be trained with data-dependent constraints to satisfyfairness goals, reduce churn, achieve a targeted false positive rate, or otherpolicy goals. We study the generalization performance for such constrainedoptimization problems, in terms of how well the constraints are satisfied atevaluation time, given that they are satisfied at training time. To improvegeneralization performance, we frame the problem as a two-player game where oneplayer optimizes the model parameters on a training dataset, and the otherplayer enforces the constraints on an independent validation dataset. We buildon recent work in two-player constrained optimization to show that if one usesthis two-dataset approach, then constraint generalization can be significantlyimproved. As we illustrate experimentally, this approach works not only intheory, but also in practice.

Training Well-Generalizing Classifiers for Fairness Metrics and Other Data-Dependent Constraints