This paper considers the generation of prediction intervals (PIs) by neural networks for quantifying uncertainty in regression tasks. It is axiomatic that high-quality PIs should be as narrow as possible, whilst capturing a specified portion of data. We derive a loss function directly from this axiom that requires no distributional assumption. We show how its form derives from a likelihood principle, that it can be used with gradient descent, and that model uncertainty is accounted for in ensembled form. Benchmark experiments show the method outperforms current state-of-the-art uncertainty quantification methods, reducing average PI width by over 10%.
Tim Pearce (University of Cambridge / The Alan Turing Institute)
Mohamed Zaki (University of Cambridge)
Related Events (a corresponding poster, oral, or spotlight)
2018 Oral: High-Quality Prediction Intervals for Deep Learning: A Distribution-Free, Ensembled Approach »
Fri Jul 13th 02:20 -- 02:30 PM Room K1