CLAPS integrates heteroscedastic last-layer Laplace uncertainty as a local scale in split conformal regression to produce intervals that adapt to both aleatoric and epistemic uncertainty while preserving nominal coverage.
Probabilistic conformal prediction with approximate conditional validity
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
A new kernel nonconformity score for multivariate conformal prediction that adapts to residual geometry, provides finite-sample coverage, and achieves convergence rates based on effective kernel rank rather than ambient dimension.
citing papers explorer
-
CLAPS: Aleatoric-Epistemic Scaling via Last-Layer Laplace for Conformal Regression
CLAPS integrates heteroscedastic last-layer Laplace uncertainty as a local scale in split conformal regression to produce intervals that adapt to both aleatoric and epistemic uncertainty while preserving nominal coverage.
-
A Kernel Nonconformity Score for Multivariate Conformal Prediction
A new kernel nonconformity score for multivariate conformal prediction that adapts to residual geometry, provides finite-sample coverage, and achieves convergence rates based on effective kernel rank rather than ambient dimension.