Pith. sign in

REVIEW 1 cited by

Conformal Validity Guarantees Exist for Any Data Distribution (and How to Find Them)

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 2405.06627 v3 pith:XLCK7Y5D submitted 2024-05-10 cs.LG cs.AIstat.ML

classification cs.LGcs.AIstat.ML
keywords datadistributionconformalalgorithmslearningshiftsactiveblack-box
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

As artificial intelligence (AI) / machine learning (ML) gain widespread adoption, practitioners are increasingly seeking means to quantify and control the risk these systems incur. This challenge is especially salient when such systems have autonomy to collect their own data, such as in black-box optimization and active learning, where their actions induce sequential feedback-loop shifts in the data distribution. Conformal prediction is a promising approach to uncertainty and risk quantification, but prior variants' validity guarantees have assumed some form of ``quasi-exchangeability'' on the data distribution, thereby excluding many types of sequential shifts. In this paper we prove that conformal prediction can theoretically be extended to \textit{any} joint data distribution, not just exchangeable or quasi-exchangeable ones. Although the most general case is exceedingly impractical to compute, for concrete practical applications we outline a procedure for deriving specific conformal algorithms for any data distribution, and we use this procedure to derive tractable algorithms for a series of AI/ML-agent-induced covariate shifts. We evaluate the proposed algorithms empirically on synthetic black-box optimization and active learning tasks.

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. Calibrating Wireless AI via Meta-Learned Context-Dependent Conformal Prediction

    eess.SP 2025-01 conditional novelty 6.0 of 10

    ML-WCP meta-learns a context-dependent likelihood ratio and uses it inside weighted conformal prediction to calibrate wireless AI with zero runtime data.

Pith tools