2022

Conformal Prediction with Temporal Quantile Adjustments

Lin, Zhen, Trivedi, Shubhendu, Sun, Jimeng

Understand

We develop Temporal Quantile Adjustment (TQA), a general method to construct efficient and valid prediction intervals (PIs) for regression on cross-sectional time series data.

Such data is common in many domains, including econometrics and healthcare.
A canonical example in healthcare is predicting patient outcomes using physiological time-series data, where a population of patients composes a cross-section.
Reliable PI estimators in this setting must address two distinct notions of coverage: cross-sectional coverage across a cross-sectional slice, and longitudinal coverage along the temporal dimension for each time series.

Built on

Regression quantiles
Roger Koenker and Gilbert Bassett · 1978
Earlier work this paper cites.
Bayesian learning via stochastic dynamics
Radford Neal · 1992
Earlier work this paper cites.
Long short-term memory
Sepp Hochreiter and Jürgen Schmidhuber · 1997
Earlier work this paper cites.
Transduction with confidence and credibility
Craig Saunders, Alexander Gammerman, and Vladimir Vovk · 1999
Earlier work this paper cites.
PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals
A. L. Goldberger, L. A. Amaral, L. Glass, J. M. Hausdorff, P. C. Ivanov, R. G. Mark, J. E. Mietus, G. B. Moody, C. K. Peng, and H. E. Stanley · 2000
Earlier work this paper cites.
Computationally efficient transductive machines
Craig Saunders, Alexander Gammerman, and Vladimir Vovk · 2000
Earlier work this paper cites.
Inductive confidence machines for regression
Harris Papadopoulos, Kostas Proedrou, Vladimir Vovk, and Alexander Gammerman · 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.
Algorithmic learning in a random world
Vladimir Vovk, Alexander Gammerman, and Glenn Shafer · 2005
Earlier work this paper cites.
Inductive conformal prediction: Theory and application to neural networks
Harris Papadopoulos · 2008
Earlier work this paper cites.
Estimating conditional quantiles with the help of the pinball loss
Ingo Steinwart and Andreas Christmann · 2011
Earlier work this paper cites.
Bayesian learning via stochastic gradient langevin dynamics
Max Welling and Yee Whye Teh · 2011
Earlier work this paper cites.
Distribution-free prediction sets
Jing Lei, James M. Robins, and Larry A. Wasserman · 2013
Earlier work this paper cites.
Conditional validity of inductive conformal predictors
Vladimir Vovk · 2013
Earlier work this paper cites.
Stochastic gradient hamiltonian monte carlo
Tianqi Chen, Emily Fox, and Carlos Guestrin · 2014
Earlier work this paper cites.
Auto-encoding variational bayes
Diederik P. Kingma and Max Welling · 2014
Earlier work this paper cites.
Distribution-free prediction bands for non-parametric regression
Jing Lei and Larry Wasserman · 2014
Earlier work this paper cites.
Adam: A method for stochastic optimization
Diederik P. Kingma and Jimmy Ba · 2015
Earlier work this paper cites.
A conformal prediction approach to explore functional data
Jing Lei, Alessandro Rinaldo, and Larry Wasserman · 2015
Earlier work this paper cites.

Similar

Dropout as a Bayesian approximation: Representing model uncertainty in deep learning
Yarin Gal and Zoubin Ghahramani · 2016
Cited alongside, same era.
Probabilistic energy forecasting: Global energy forecasting competition 2014 and beyond
Tao Hong, Pierre Pinson, Shu Fan, Hamidreza Zareipour, Alberto Troccoli, and Rob J. Hyndman · 2016
Cited alongside, same era.
MIMIC-III, a freely accessible critical care database
Alistair E.W. Johnson, Tom J. Pollard, Lu Shen, Li-wei H. Lehman, Mengling Feng, Mohammad Ghassemi, Benjamin Moody, Peter Szolovits, Leo Anthony Celi, and Roger G. Mark · 2016
Cited alongside, same era.
Bayesian recurrent neural networks
Original
Meire Fortunato, Charles Blundell, and Oriol Vinyals · 2017
Cited alongside, same era.
Simple and scalable predictive uncertainty estimation using deep ensembles
Balaji Lakshminarayanan, Alexander Pritzel, and Charles Blundell · 2017
Cited alongside, same era.
Multiplicative normalizing flows for variational Bayesian neural networks
Christos Louizos and Max Welling · 2017
Cited alongside, same era.
A multi-horizon quantile recurrent forecaster, 2017
Ruofeng Wen, Kari Torkkola, Balakrishnan Narayanaswamy, and Dhruv Madeka · 2017
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.
Concepts and applications of conformal prediction in computational drug discovery
Original
Isidro Cortés-Ciriano and Andreas Bender · 2019
Cited alongside, same era.
Probabilistic forecasting with spline quantile function rnns
Jan Gasthaus, Konstantinos Benidis, Yuyang Wang, Syama Sundar Rangapuram, David Salinas, Valentin Flunkert, and Tim Januschowski · 2019
Cited alongside, same era.
Mimic-iii clinical database demo (version 1.4)
A. Johnson, T. Pollard, and R. Mark · 2019
Cited alongside, same era.
Inductive conformal predictor for convolutional neural networks: Applications to active learning for image classification
Sergio Matiz and Kenneth E. Barner · 2019
Cited alongside, same era.

Then

Distribution-free, risk-controlling prediction sets
Stephen Bates, A. Angelopoulos, Lihua Lei, Jitendra Malik, and Michael I. Jordan · 2021
Later among the works it cites.
A probabilistic bayesian recurrent neural network for remaining useful life prognostics considering epistemic and aleatory uncertainties
Jose Caceres, Danilo Gonzalez, Taotao Zhou, and Enrique Lopez Droguett · 2021
Later among the works it cites.
Adaptive conformal inference under distribution shift
Isaac Gibbs and Emmanuel Candes · 2021
Later among the works it cites.
Locally valid and discriminative prediction intervals for deep learning models
Zhen Lin, Shubhendu Trivedi, and Jimeng Sun · 2021
Later among the works it cites.
Distribution-free uncertainty quantification for classification under label shift
Aleksandr Podkopaev and Aaditya Ramdas · 2021
Later among the works it cites.
Conformal time-series forecasting
Kamilė Stankevičiūtė, Ahmed Alaa, and Mihaela van der Schaar · 2021
Later among the works it cites.
Conformal prediction interval for dynamic time-series
Chen Xu and Yao Xie · 2021
Later among the works it cites.
Deep learning-based conformal prediction of toxicity
Original
Jin Zhang, Ulf Norinder, and Fredrik Svensson · 2021
Later among the works it cites.
Image-to-image regression with distribution-free uncertainty quantification and applications in imaging
Original
Anastasios Nikolas Angelopoulos, Amit Kohli, Stephen Bates, Michael I. Jordan, Jitendra Malik, Thayer Alshaabi, Srigokul Upadhyayula, and Yaniv Romano · 2022
Closest in time.
Conformal prediction beyond exchangeability, 2022
Rina Foygel Barber, Emmanuel J. Candes, Aaditya Ramdas, and Ryan J. Tibshirani · 2022
Closest in time.
https://https://coronavirus.data.gov.uk/ , 2022
Coronavirus (covid-19) in the uk · 2022
Closest in time.
Conformal prediction for the design problem
Original
Clara Fannjiang, Stephen Bates, Anastasios Nikolas Angelopoulos, Jennifer Listgarten, and Michael I. Jordan · 2022
Closest in time.
Split conformal prediction for dependent data, 2022
Roberto I. Oliveira, Paulo Orenstein, Thiago Ramos, and João Vitor Romano · 2022
Closest in time.
Pac prediction sets under covariate shift
Sangdon Park, Edgar Dobriban, Insup Lee, and Osbert Bastani · 2022
Closest in time.
Distribution-free prediction sets adaptive to unknown covariate shift, 2022
Hongxiang Qiu, Edgar Dobriban, and Eric Tchetgen Tchetgen · 2022
Closest in time.
https://archive.ics.uci.edu/ml/datasets/EEG+Database , 1999
Eeg database · 2022
Closest in time.
Doubly robust calibration of prediction sets under covariate shift, 2022
Yachong Yang, Arun Kumar Kuchibhotla, and Eric Tchetgen Tchetgen · 2022
Closest in time.
Adaptive conformal predictions for time series, 2022
Margaux Zaffran, Aymeric Dieuleveut, Olivier Féron, Yannig Goude, and Julie Josse · 2022
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…