Calibrated Reliable Regression using Maximum Mean Discrepancy

06/18/2020
by   Peng Cui, et al.
0

Accurate quantification of uncertainty is crucial for real-world applications of machine learning. However, modern deep neural networks still produce unreliable predictive uncertainty, often yielding over-confident predictions. In this paper, we are concerned with getting well-calibrated predictions in regression tasks. We propose the calibrated regression method using the maximum mean discrepancy for distribution level calibration. Theoretically, the calibration error of our method asymptotically converges to zero when the sample size is large enough. Experiments on non-trivial real datasets show that our method can produce well-calibrated and sharp prediction intervals, which outperforms the related state-of-the-art methods.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/15/2021

Revisiting the Calibration of Modern Neural Networks

Accurate estimation of predictive uncertainty (model calibration) is ess...
research
12/20/2020

Towards Trustworthy Predictions from Deep Neural Networks with Fast Adversarial Calibration

To facilitate a wide-spread acceptance of AI systems guiding decision ma...
research
03/28/2021

Accurate and Reliable Forecasting using Stochastic Differential Equations

It is critical yet challenging for deep learning models to properly char...
research
03/26/2018

Calibrated Prediction Intervals for Neural Network Regressors

Ongoing developments in neural network models are continually advancing ...
research
08/26/2019

Marginally-calibrated deep distributional regression

Deep neural network (DNN) regression models are widely used in applicati...
research
02/21/2023

Posterior Annealing: Fast Calibrated Uncertainty for Regression

Bayesian deep learning approaches that allow uncertainty estimation for ...
research
07/04/2021

Calibrating generalized predictive distributions

In prediction problems, it is common to model the data-generating proces...

Please sign up or login with your details

Forgot password? Click here to reset