AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Metrics of Calibration for Probabilistic Predictions

Imanol Arrieta-Ibarra, Paman Gujral, Jonathan Tannen, Mark Tygert, Cherie Xu

JMLR 2022 · Learning theory and algorithms › Prediction and decision losses · approach: Probabilistic calibration · 20 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 cumulative-difference ECCE statistics instead of binned ECEcalibration metric · synthetic data, growing sample sizeability to separate perfect from imperfect calibrationImproved
increase number of observationsECCE for perfectly calibrated data · synthetic dataECCEImproved
increase number of observationsECE for perfectly calibrated data · synthetic dataECENo clear effect
use ECCE-MAD/sigma_n on perfectly calibrated dataECCE-MAD · synthetic dataexpected value: 1.2533No clear effect
use ECCE-R/sigma_n on perfectly calibrated dataECCE-R · synthetic dataexpected value: 1.5958No clear effect
use cumulative plots instead of reliability diagramscalibration visualization · ImageNet subsetsreveals miscalibration without binningImproved

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