Pith. sign in

REVIEW 4 cited by

Machine Learning with a Reject Option: A survey

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2107.11277 v3 pith:6VGT5ABU submitted 2021-07-23 cs.LG cs.AI

classification cs.LGcs.AI
keywords learningmachinerejectionmodelslikelymakepredictionsurvey
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Machine learning models always make a prediction, even when it is likely to be inaccurate. This behavior should be avoided in many decision support applications, where mistakes can have severe consequences. Albeit already studied in 1970, machine learning with rejection recently gained interest. This machine learning subfield enables machine learning models to abstain from making a prediction when likely to make a mistake. This survey aims to provide an overview on machine learning with rejection. We introduce the conditions leading to two types of rejection, ambiguity and novelty rejection, which we carefully formalize. Moreover, we review and categorize strategies to evaluate a model's predictive and rejective quality. Additionally, we define the existing architectures for models with rejection and describe the standard techniques for learning such models. Finally, we provide examples of relevant application domains and show how machine learning with rejection relates to other machine learning research areas.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Removable Defects: The Economics and Limits of Deliberate Deficiency

    econ.EM 2026-07 unverdicted novelty 7.0 of 10

    A deliberately narrow specialist can profitably keep a defect only when the detector that triggers compensation sits outside the defect; inside, the miss rate equals the capture rate.

  2. Polyra Swarms: A Shape-Based Approach to Machine Learning

    cs.LG 2025-06 conditional novelty 6.0 of 10

    Polyra Swarms approximate data distributions as logical combinations of polytopes, achieving competitive anomaly detection and enabling symbolic abstraction to simple rules.

  3. Conservative classifiers do consistently well with improving agents: characterizing statistical and online learning

    cs.LG 2025-06 conditional novelty 6.0 of 10

    The paper gives an exact characterization of which concept classes are properly PAC-learnable with improving agents, plus new positive results for improper learning under coverable distributions, learning with bounded...

  4. Clustered Calibration: Representation-Aware Probability Calibration via Learned Subpopulations

    cs.LG 2025-10 reject novelty 5.0 of 10

    Clustered Calibration groups samples by learned representations and calibrates each cluster separately, with a new cluster-binned ECE claimed to rank models by both calibration and AUC.

Pith tools