Reliable Prediction Intervals with Regression Neural Networks
This addresses the need for uncertainty quantification in regression tasks, particularly for applications like trans-ionospheric links, but it is incremental as it builds on the Conformal Prediction framework.
The paper tackles the problem of providing reliable prediction intervals for regression neural networks, achieving well-calibrated and tight intervals on benchmark datasets and a large TEC dataset with over 60,000 measurements.
This paper proposes an extension to conventional regression Neural Networks (NNs) for replacing the point predictions they produce with prediction intervals that satisfy a required level of confidence. Our approach follows a novel machine learning framework, called Conformal Prediction (CP), for assigning reliable confidence measures to predictions without assuming anything more than that the data are independent and identically distributed (i.i.d.). We evaluate the proposed method on four benchmark datasets and on the problem of predicting Total Electron Content (TEC), which is an important parameter in trans-ionospheric links; for the latter we use a dataset of more than 60000 TEC measurements collected over a period of 11 years. Our experimental results show that the prediction intervals produced by our method are both well-calibrated and tight enough to be useful in practice.