Empirical Frequentist Coverage of Deep Learning Uncertainty Quantification Procedures

Uncertainty quantification for complex deep learning models is increasingly important as these techniques see growing use in high-stakes, real-world settings. Currently, the quality of a model's uncertainty is evaluated using point-prediction metrics such as negative log-likelihood or the Brier score on heldout data. In this study, we provide the first large scale evaluation of the empirical frequentist coverage properties of well known uncertainty quantification techniques on a suite of regression and classification tasks. We find that, in general, some methods do achieve desirable coverage properties on in distribution samples, but that coverage is not maintained on out-of-distribution data. Our results demonstrate the failings of current uncertainty quantification techniques as dataset shift increases and establish coverage as an important metric in developing models for real-world applications.

[1]  Sebastian Nowozin,et al.  How Good is the Bayes Posterior in Deep Neural Networks Really? , 2020, ICML.

[2]  Dustin Tran,et al.  Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batches , 2018, ICLR.

[3]  Larry Wasserman,et al.  All of Statistics: A Concise Course in Statistical Inference , 2004 .

[4]  Dustin Tran,et al.  Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness , 2020, NeurIPS.

[5]  Geoffrey E. Hinton,et al.  Bayesian Learning for Neural Networks , 1995 .

[6]  Ben Glocker,et al.  Implicit Weight Uncertainty in Neural Networks. , 2017 .

[7]  Andrew Gordon Wilson,et al.  A Simple Baseline for Bayesian Uncertainty in Deep Learning , 2019, NeurIPS.

[8]  Kevin Gimpel,et al.  A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks , 2016, ICLR.

[9]  Richard E. Turner,et al.  Black-box α-divergence minimization , 2016, ICML 2016.

[10]  Van Der Vaart,et al.  The Bernstein-Von-Mises theorem under misspecification , 2012 .

[11]  Alex Graves,et al.  Practical Variational Inference for Neural Networks , 2011, NIPS.

[12]  Julien Cornebise,et al.  Weight Uncertainty in Neural Networks , 2015, ArXiv.

[13]  Charles Blundell,et al.  Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles , 2016, NIPS.

[14]  Jasper Snoek,et al.  Deep Bayesian Bandits Showdown: An Empirical Comparison of Bayesian Deep Networks for Thompson Sampling , 2018, ICLR.

[15]  E. Candès,et al.  The limits of distribution-free conditional predictive inference , 2019, Information and Inference: A Journal of the IMA.

[16]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[17]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[18]  Ryan P. Adams,et al.  Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks , 2015, ICML.

[19]  B. Efron,et al.  The Jackknife: The Bootstrap and Other Resampling Plans. , 1983 .

[20]  Jürgen Schmidhuber,et al.  Training Very Deep Networks , 2015, NIPS.

[21]  Julien Cornebise,et al.  Weight Uncertainty in Neural Network , 2015, ICML.

[22]  Zoubin Ghahramani,et al.  Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning , 2015, ICML.

[23]  Kilian Q. Weinberger,et al.  On Calibration of Modern Neural Networks , 2017, ICML.

[24]  Max Welling,et al.  Multiplicative Normalizing Flows for Variational Bayesian Neural Networks , 2017, ICML.

[25]  Soumya Ghosh,et al.  Quality of Uncertainty Quantification for Bayesian Neural Network Inference , 2019, ArXiv.

[26]  Yee Whye Teh,et al.  Simple and Scalable Epistemic Uncertainty Estimation Using a Single Deep Deterministic Neural Network , 2020, ICML.

[27]  Max Welling,et al.  Structured and Efficient Variational Deep Learning with Matrix Gaussian Posteriors , 2016, ICML.

[28]  S. Lahiri,et al.  Bootstrapping Lasso Estimators , 2011 .

[29]  B. Efron.  The jackknife, the bootstrap, and other resampling plans , 1987 .

[30]  Sebastian Nowozin,et al.  Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift , 2019, NeurIPS.