Localized Conformal Prediction: A Generalized Inference Framework for Conformal Prediction
By Leying Guan. Biometrika, 2021
163 citations recorded by the source corpus.
We propose a new inference framework called localized conformal prediction. It generalizes the framework of conformal prediction by offering a single-test-sample adaptive construction that emphasizes a local region around this test sample, and can be combined with different conformal scores. The proposed framework enjoys an assumption-free finite sample marginal coverage guarantee, and it also offers additional local coverage guarantees under suitable assumptions. We demonstrate how to change from conformal prediction to localized conformal prediction using several conformal scores, and we illustrate a potential gain via numerical examples.
Subfields: Civil and Structural Engineering, Mechanical Engineering
View Paper: https://www.semanticscholar.org/paper/1fa186ef8f06071396bd516fb8e4f50f47bc2635
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Civil and Structural Engineering
In Mechanical Engineering
Citations in the corpus
- Conformal prediction with conditional guarantees (2023, unknown): “…there are some minor extensions to this procedure, such as Mondrian conformal prediction, that provide conditional guarantees, these methods are quite limited and can only achieve conditional coverage over a small number of pre-specified, disjoint groups (Vovk et al. (2003), Romano et al. (2020a)).”
- Conformal prediction beyond exchangeability (2022, background): “, 2019] and/or localized conformal prediction (LCP) [Guan, 2021] methods, where the weight wi (and, potentially, the tag ti) placed on data point i might now additionally incorporate data-dependent information—e.”