REVIEW 7 cited by
Conformal Prediction With Conditional Guarantees
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
read the original abstract
We consider the problem of constructing distribution-free prediction sets with finite-sample conditional guarantees. Prior work has shown that it is impossible to provide exact conditional coverage universally in finite samples. Thus, most popular methods only guarantee marginal coverage over the covariates or are restricted to a limited set of conditional targets, e.g. coverage over a finite set of pre-specified subgroups. This paper bridges this gap by defining a spectrum of problems that interpolate between marginal and conditional validity. We motivate these problems by reformulating conditional coverage as coverage over a class of covariate shifts. When the target class of shifts is finite-dimensional, we show how to simultaneously obtain exact finite-sample coverage over all possible shifts. For example, given a collection of subgroups, our prediction sets guarantee coverage over each group. For more flexible, infinite-dimensional classes where exact coverage is impossible, we provide a procedure for quantifying the coverage errors of our algorithm. Moreover, by tuning interpretable hyperparameters, we allow the practitioner to control the size of these errors across shifts of interest. Our methods can be incorporated into existing split conformal inference pipelines, and thus can be used to quantify the uncertainty of modern black-box algorithms without distributional assumptions.
Forward citations
Cited by 7 Pith papers
-
Simultaneous Coverage and Efficiency Guarantee in Online Conformal Prediction
Simultaneous non-cancelling coverage and efficiency guarantees are derived for online conformal prediction in adversarial, stochastic, and covariate-dependent settings, with a matching minimax rate for the stochastic ...
-
Isotonic Conformal Prediction
Isotonic Conformal Prediction achieves prediction-conditional coverage with one isotonic fit, via a split variant (SICP) and an exact transductive variant (TICP).
-
SpeedCP: Fast Kernel-based Conditional Conformal Prediction
SpeedCP traces the regularization and score solution paths of RKHS quantile regression, making RKHS-based conditional conformal prediction fast and adaptable to low-rank latent embeddings.
-
Multiply Robust Conformal Risk Control with Coarsened Data
A conformal risk control framework using efficient influence functions yields distribution-free prediction sets for outcomes trained on coarsened, missing, or censored data.
-
Direct Prediction Set Minimization via Bilevel Conformal Classifier Training
DPSM reformulates conformal training as a bilevel problem with quantile regression in the lower level and claims an O(1/sqrt n) learning bound, cutting prediction set size by about 20% in experiments.
-
Response Quality Assessment for Retrieval-Augmented Generation via Conditional Conformal Factuality
Conformal-RAG applies conformal prediction with a retrieval-based relevance score to guarantee the factuality of retained sub-claims in RAG responses.
-
On the Need to Align Intent and Implementation in Uncertainty Quantification for Machine Learning
A position paper framing the mismatch between uncertainty quantities and their intended scientific claims as 'construct drift,' and proposing trustworthiness axes for scientific ML.
Discussion (0). Continue with ORCID to comment.