A comparison of some conformal quantile regression methods
From MaRDI portal
Abstract: We compare two recently proposed methods that combine ideas from conformal inference and quantile regression to produce locally adaptive and marginally valid prediction intervals under sample exchangeability (Romano et al., 2019; Kivaranovic et al., 2019). First, we prove that these two approaches are asymptotically efficient in large samples, under some additional assumptions. Then we compare them empirically on simulated and real data. Our results demonstrate that the method in Romano et al. (2019) typically yields tighter prediction intervals in finite samples. Finally, we discuss how to tune these procedures by fixing the relative proportions of observations used for training and conformalization.
Cited in
(11)- Conditional validity of heteroskedastic conformal regression
- Conformal prediction with conditional guarantees
- Conformal prediction with local weights: randomization enables robust guarantees
- Algorithmic stability implies training-conditional coverage for distribution-free prediction methods
- Conformal inference for random objects
- Conformal load prediction with transductive graph autoencoders
- Selection and Aggregation of Conformal Prediction Sets
- A review of recent advances in high-dimensional quantile regression
- Highest Probability Density Conformal Regions
- TorchCP: a Python library for conformal prediction
- Conformalized robust principal component analysis
This page was built for publication: A comparison of some conformal quantile regression methods
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6325140)
