• Corpus ID: 201645293

Conformal prediction with localization

  title={Conformal prediction with localization},
  author={Leying Guan},
  journal={arXiv: Statistics Theory},
  • Leying Guan
  • Published 22 August 2019
  • Mathematics, Computer Science
  • arXiv: Statistics Theory
We propose a new method called localized conformal prediction, where we can perform conformal inference using only a local region around a new test sample to construct its confidence interval. Localized conformal inference is a natural extension to conformal inference. It generalizes the method of conformal prediction to the case where we can break the data exchangeability, so as to give the test sample a special role. To our knowledge, this is the first work that introduces such a localization… 

Figures and Tables from this paper

Split Localized Conformal Prediction

A modified non-conformity score is proposed, which is simple andcient compared with full conformal methods but better approximates conditional coverage guarantee, and provides tighter intervals compared to existing methods.

MD-split+: Practical Local Conformal Inference in High Dimensions

This work presents MD-split+, a practical local conformal approach that creates X partitions based on localized model performance of conditional density estimation models, and handles complex real-world data settings where such models may be misspecified, and scales to high-dimensional inputs.

Nested Conformal Prediction and the Generalized Jackknife

Abstract: We provide an alternate unified framework for conformal prediction, which is a framework to provide assumption-free prediction intervals. Instead of beginning by choosing a conformity

Efficient and Differentiable Conformal Prediction with General Function Classes

This meta-algorithm generalizes existing conformal prediction algorithms, and it achieves approximate valid population coverage and near-optimal efficiency within class, whenever the function class in the conformalization step is low-capacity in a certain sense.

Conformal Risk Control

The algorithm generalizes split conformal prediction together with its coverage guarantee and is able to bound the false negative rate, graph distance, and token-level F1-score.

CD-split: efficient conformal regions in high dimensions

It is shown that CD-split converges asymptotically to the oracle highest density set and satisfies local and asymPTotic conditional validity, and has a better conditional coverage and yields smaller prediction regions than other methods.

Distribution-free conditional predictive bands using density estimators

Two conformal methods based on conditional density estimators that do not depend on this type of assumption to obtain asymptotic conditional coverage are introduced: Dist-split and CD-split.

Valid model-free spatial prediction

Predicting the response at an unobserved location is a fundamental problem in spatial statistics. Given the difficulty in modeling spatial dependence, especially in non-stationary cases, model-based

Distribution-free conditional median inference

A method is proposed based upon ideas from conformal prediction and a theoretical guarantee of coverage is established while also going over particular distributions where its performance is sharp, resulting in a lower bound on the length of any possible conditional median confidence interval.



Conformal Prediction Under Covariate Shift

It is shown that a weighted version of conformal prediction can be used to compute distribution-free prediction intervals for problems in which the test and training covariate distributions differ, but the likelihood ratio between these two distributions is known.

A conformal prediction approach to explore functional data

While ordinary conformal prediction has high computational cost for functional data, this paper uses the inductive conformal predictor, together with several novel choices of conformity scores, to simplify the computation.

A tutorial on conformal prediction

This tutorial presents a self-contained account of the theory of conformal prediction and works through several numerical examples of how the model under which successive examples are sampled independently from the same distribution can be applied to any method for producing ŷ.

Conformalized Quantile Regression

This paper proposes a new method that is fully adaptive to heteroscedasticity, which combines conformal prediction with classical quantile regression, inheriting the advantages of both.

Distribution-Free Predictive Inference for Regression

A general framework for distribution-free predictive inference in regression, using conformal inference, which allows for the construction of a prediction band for the response variable using any estimator of the regression function, and a model-free notion of variable importance, called leave-one-covariate-out or LOCO inference.

A comparison of some conformal quantile regression methods

We compare two recent methods that combine conformal inference with quantile regression to produce locally adaptive and marginally valid prediction intervals under sample exchangeability (Romano,

Distribution-free conditional predictive bands using density estimators

Two conformal methods based on conditional density estimators that do not depend on this type of assumption to obtain asymptotic conditional coverage are introduced: Dist-split and CD-split.

Distribution‐free prediction bands for non‐parametric regression

A new prediction band is given by combining the idea of ‘conformal prediction’ with non‐parametric conditional density estimation and the proposed estimator, called COPS, always has a finite sample guarantee.

Conditional validity of inductive conformal predictors

  • V. Vovk
  • Mathematics
    Machine Learning
  • 2013
Various versions of conditional validity and various ways to achieve them using inductive conformal predictors and their modifications are explored, including a convenient expression of one of the modifications in terms of ROC curves.

The limits of distribution-free conditional predictive inference

This work aims to explore the space in between exact conditional inference guarantees and what types of relaxations of the conditional coverage property would alleviate some of the practical concerns with marginal coverage guarantees while still being possible to achieve in a distribution-free setting.