Pith. sign in

REVIEW 1 cited by

Selective Ensembles for Consistent Predictions

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 2111.08230 v1 pith:ORH6TKIK submitted 2021-11-16 cs.LG

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

Recent work has shown that models trained to the same objective, and which achieve similar measures of accuracy on consistent test data, may nonetheless behave very differently on individual predictions. This inconsistency is undesirable in high-stakes contexts, such as medical diagnosis and finance. We show that this inconsistent behavior extends beyond predictions to feature attributions, which may likewise have negative implications for the intelligibility of a model, and one's ability to find recourse for subjects. We then introduce selective ensembles to mitigate such inconsistencies by applying hypothesis testing to the predictions of a set of models trained using randomly-selected starting conditions; importantly, selective ensembles can abstain in cases where a consistent outcome cannot be achieved up to a specified confidence level. We prove that that prediction disagreement between selective ensembles is bounded, and empirically demonstrate that selective ensembles achieve consistent predictions and feature attributions while maintaining low abstention rates. On several benchmark datasets, selective ensembles reach zero inconsistently predicted points, with abstention rates as low 1.5%.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

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

  1. VirnyFlow: A Design Space for Responsible Model Development

    cs.LG 2025-06 reject novelty 5.0 of 10

    VirnyFlow is a distributed ML pipeline optimizer that lets users define fairness, stability, and accuracy as weighted objectives and claims to outperform AutoML baselines.

Pith tools