Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Conformalized-DeepONet: A Distribution-Free Framework for Uncertainty Quantification in Deep Operator Networks

About

In this paper, we adopt conformal prediction, a distribution-free uncertainty quantification (UQ) framework, to obtain confidence prediction intervals with coverage guarantees for Deep Operator Network (DeepONet) regression. Initially, we enhance the uncertainty quantification frameworks (B-DeepONet and Prob-DeepONet) previously proposed by the authors by using split conformal prediction. By combining conformal prediction with our Prob- and B-DeepONets, we effectively quantify uncertainty by generating rigorous confidence intervals for DeepONet prediction. Additionally, we design a novel Quantile-DeepONet that allows for a more natural use of split conformal prediction. We refer to this distribution-free effective uncertainty quantification framework as split conformal Quantile-DeepONet regression. Finally, we demonstrate the effectiveness of the proposed methods using various ordinary, partial differential equation numerical examples, and multi-fidelity learning.

Christian Moya, Amirhossein Mollaali, Zecheng Zhang, Lu Lu, Guang Lin• 2024

Related benchmarks

TaskDatasetResultRank
Air Quality Predictionair quality
FC0.565
9
Energy forecastingEnergy Demand
FC49.6
9
Uncertainty QuantificationReg-GP1D Global Heterogeneity Gaussian process simulations (test)
Fidelity Coverage (FC)52.7
9
Uncertainty QuantificationAR-GP1D Spectral Heterogeneity Gaussian process simulations (test)
FC0.206
9
Uncertainty QuantificationAR-GP2D Local Heterogeneity (test)
FC0.00e+0
9
Weather forecastingWeather-ERA5
FC Score0.00e+0
9
Showing 6 of 6 rows

Other info

Follow for update