AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Fisher Consistency for Prior Probability Shift

Dirk Tasche

JMLR 2017 · Label-efficient and robust learning › Recognition and long-tail · approach: Learning from unlabeled and positive-unlabeled data · 29 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use ACC or EM instead of CDE-Iterate under prior probability shiftCDE-Iterate · Binormal test, population, Q[Y=0]=0.1estimated class 0 prevalence: 0.0121 -> 0.1000Improved
run CDE-Iterate to the second iteration instead of the first (ablation)CDE-Iterate · Binormal test, population, Q[Y=0]=0.1estimated class 0 prevalence: 0.2269 -> 0.1131Improved
run CDE-Iterate to convergence instead of the second iteration (ablation)CDE-Iterate · Binormal test, population, Q[Y=0]=0.1estimated class 0 prevalence: 0.1131 -> 0.0121Hurt
replace ACC by EM under invariant density ratio shiftACC · Non-normal test with binormal density ratio, population, Q[Y=0]=0.1estimated class 0 prevalence: 0.0958 -> 0.1000Improved
use CDE2 instead of ACC outside prior probability shiftACC · Non-normal test with binormal density ratio, sample, Q[Y=0]=0.1estimated class 0 prevalence: 0.0828 -> 0.1014No clear effect
use EM when density ratio is not invariantEM · Non-normal test with non-binormal density ratio, population, Q[Y=0]=0.01estimated class 0 prevalence: 0.0100 -> 0.1307Hurt
use ACC when test set deviates from prior probability shiftACC · Non-normal test with non-binormal density ratio, population, Q[Y=0]=0.99estimated class 0 prevalence: 0.9900 -> 0.8230Hurt
use CDE-infinity instead of CDE1 or CDE2 when density ratio is square-rootedCDE-Iterate · Non-normal test with non-binormal density ratio, population, Q[Y=0]=0.01estimated class 0 prevalence: 0.2664 -> 0.0000Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy