computer-vision-1

Conformal Prediction

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in conformal-prediction-1

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find conformal-prediction-1 models and implementations

scikit-learn-contrib/mapie

2 papers 1,151

Datasets

No datasets available.

Subtasks

No subtasks available.

Most implemented papers

Uncertainty Sets for Image Classifiers using Conformal Prediction

Michael I. Jordan, J. Malik, Anastasios Nikolas Angelopoulos, Stephen Bates•Mon Sep 28 2020

An algorithm is presented that modifies any classifier to output a predictive set containing the true label with a user-specified probability, such as 90%, which provides a formal finite-sample coverage guarantee for every model and dataset.

427

Content

lightning-uq-box/lightning-uq-box

2 papers 72

0

Paper Graph

Conformalized Quantile Regression

E. Candès, Yaniv Romano, Evan Patterson•Tue May 07 2019

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.

801 0

Paper Graph

A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification

Anastasios Nikolas Angelopoulos, Stephen Bates•Wed Jul 14 2021

This hands-on introduction is aimed to provide the reader a working understanding of conformal prediction and related distribution-free uncertainty quantification techniques with one self-contained document.

866 0

Paper Graph

An Exact and Robust Conformal Inference Method for Counterfactual and Synthetic Controls

V. Chernozhukov, Kaspar Wüthrich, Yinchu Zhu•Sun Dec 24 2017

The causal inference problem is recast as a counterfactual prediction and a structural breaks testing problem to develop permutation inference procedures that accommodate modern high-dimensional estimators, are valid under weak and easy-to-verify conditions, and are provably robust against misspecification.

234 0

Paper Graph

MAPIE: an open-source library for distribution-free uncertainty quantification

V. Taquet, V. Blot, Thomas Morzadec, L. Lacombe, N. Brunel•Sun Jul 24 2022

MAPIE (Model Agnostic Prediction Interval Estimator), an open-source Python library that quantifies the uncertainties of ML models for single-output regression and multi-class classification tasks, is introduced.

27 0

Paper Graph

Conformal prediction interval for dynamic time-series

Chen Xu, Yao Xie•Sat Oct 17 2020

A method to build distribution-free prediction intervals for time-series based on conformal inference that wraps around any ensemble estimator to construct sequential prediction intervals is developed, which is easy to implement, scalable to producing arbitrarily many prediction intervals sequentially, and well-suited to a wide range of regression functions.

162 0

Paper Graph

Learning Optimal Conformal Classifiers

A. Doucet, K. Dvijotham, David Stutz, Ali Taylan Cemgil•Sun Oct 17 2021

This paper explores strategies to differentiate through CP during training with the goal of training model with the conformal wrapper end-to-end, and shows ConfTr can influence how inefficiency is distributed across classes, or guide the composition of confidence sets in terms of the included classes, while retaining the guarantees offered by CP.

113 0

Paper Graph

Image-to-Image Regression with Distribution-Free Uncertainty Quantification and Applications in Imaging

Michael I. Jordan, T. Alshaabi, Anastasios Nikolas Angelopoulos, Stephen Bates, Yaniv Romano, Amit Kohli, J. Malik, S. Upadhyayula•Wed Feb 09 2022

Uncertainty quantification techniques are developed with rigorous statistical guarantees for image-to-image regression problems that derive uncertainty intervals around each pixel that are guaranteed to contain the true value with a user-specified confidence probability.

110 0

Paper Graph

Adaptive Conformal Predictions for Time Series

Margaux Zaffran, Aymeric Dieuleveut, Olivier F'eron, Y. Goude, J. Josse•Mon Feb 14 2022

This work argues that Adaptive Conformal Inference (ACI), developed for distribution-shift time series, is a good procedure for time series with general dependency, and proposes a parameter-free method, AgACI, that adaptively builds upon ACI based on online expert aggregation.

190 0

Paper Graph

Adding a benchmark result helps the community track progress.