Fetching the paper…
Reading the bibliography…
In a supervised learning problem, given a predicted value that is the output of some trained model, how can we quantify our uncertainty around this prediction? Distribution-free predictive inference aims to construct prediction intervals around this output, with valid coverage that does not rely on assumptions on the distribution of the data or the nature of the model training algorithm.
A finite sample distribution-free performance bound for local discrimination rules
William H Rogers and Terry J Wagner · 1978
Earlier work this paper cites.
Bagging predictors
Leo Breiman · 1996
Earlier work this paper cites.
Algorithmic stability and sanity-check bounds for leave-one-out cross-validation
Michael Kearns and Dana Ron · 1997
Earlier work this paper cites.
Ensemble methods in machine learning
Thomas G Dietterich · 2000
Earlier work this paper cites.
Random forests
Leo Breiman · 2001
Earlier work this paper cites.
Stability and generalization
Olivier Bousquet and André Elisseeff · 2002
Earlier work this paper cites.
Analyzing bagging
Peter Bühlmann and Bin Yu · 2002
Earlier work this paper cites.
Stability-based model selection
Tilman Lange, Mikio Braun, Volker Roth, and Joachim Buhmann · 2002
Earlier work this paper cites.
Inductive confidence machines for regression
Harris Papadopoulos, Kostas Proedrou, Volodya Vovk, and Alex Gammerman · 2002
Earlier work this paper cites.
Bagging equalizes influence
Yves Grandvalet · 2004
Cited alongside, same era.
Stability of randomized learning algorithms
Andre Elisseeff, Theodoros Evgeniou, Massimiliano Pontil, and Leslie Pack Kaelbing · 2005
Cited alongside, same era.
Algorithmic Learning in a Random World , volume 29
Vladimir Vovk, Alexander Gammerman, and Glenn Shafer · 2005
Cited alongside, same era.
Stability selection
Nicolai Meinshausen and Peter Bühlmann · 2010
Cited alongside, same era.
Conditional validity of inductive conformal predictors
Vladimir Vovk · 2012
Cited alongside, same era.
Variable selection with error control: another look at stability selection
Rajen D Shah and Richard J Samworth · 2013
Cited alongside, same era.
Cross-conformal predictors
Conformalized quantile regression
Yaniv Romano, Evan Patterson, and Emmanuel Candes · 2019
Later among the works it cites.
A comparison of some conformal quantile regression methods
Matteo Sesia and Emmanuel J Candès · 2020
Later among the works it cites.
Predictive inference with the jackknife+
Rina Foygel Barber, Emmanuel J Candes, Aaditya Ramdas, and Ryan J Tibshirani · 2021
Later among the works it cites.
Assumption-lean conditional predictive inference via the jackknife and the jackknife+
Nicolai Amann, Hannes Leeb, and Lukas Steinberger · 2023
Closest in time.
Training-conditional coverage for distribution-free predictive inference
Michael Bian and Rina Foygel Barber · 2023
Closest in time.
Black-box tests for algorithmic stability
Byol Kim and Rina Foygel Barber · 2023
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Vladimir Vovk · 2015
Cited alongside, same era.
Max-information, differential privacy, and post-selection hypothesis testing
Ryan Rogers, Aaron Roth, Adam Smith, and Om Thakkar · 2016
Cited alongside, same era.
Distribution-free predictive inference for regression
Jing Lei, Max G’Sell, Alessandro Rinaldo, Ryan J Tibshirani, and Larry Wasserman · 2018
Cited alongside, same era.
Distribution-free performance bounds for potential function rules
Luc Devroye and Terry Wagner
Cited in the paper.
Distribution-free inequalities for the deleted and holdout error estimates
Luc Devroye and Terry Wagner
Cited in the paper.
Generalization in adaptive data analysis and holdout reuse
Cynthia Dwork, Vitaly Feldman, Moritz Hardt, Toni Pitassi, Omer Reingold, and Aaron Roth
Cited in the paper.
Closest in time.
Conditional predictive inference for stable algorithms
Lukas Steinberger and Hannes Leeb · 2023
Closest in time.
Post-selection inference via algorithmic stability
Tijana Zrnic and Michael I Jordan · 2023
Closest in time.