# Reliable Prediction Intervals with Regression Neural Networks

arXiv: https://arxiv.org/abs/2312.09606 · HTML: https://mlsanity.com/paper/2312.09606/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 49 references that are in the map.
- First posted on arXiv 15 Dec 2023.

## Builds on (most cited first, 2 of 2)

- [Learning by Transduction](https://mlsanity.com/paper/1301.7375/) (2013)
- [Regression Conformal Prediction with Nearest Neighbours](https://mlsanity.com/paper/1401.3880/) (2014)

## Built on by (most cited first, 11 of 11)

- [Conformal Prediction: A Data Perspective](https://mlsanity.com/paper/2410.06494/) (2024)
- [Rectifying Conformity Scores for Better Conditional Coverage](https://mlsanity.com/paper/2502.16336/) (2025)
- [Early Time Classification with Accumulated Accuracy Gap Control](https://mlsanity.com/paper/2402.00857/) (2024)
- [TorchCP: A Python Library for Conformal Prediction](https://mlsanity.com/paper/2402.12683/) (2024)
- [Conformal Convolution and Monte Carlo Meta-learners for Predictive Inference of Individual Treatment Effects](https://mlsanity.com/paper/2402.04906/) (2024)
- [Conformalized Selective Regression](https://mlsanity.com/paper/2402.16300/) (2024)
- [Reliable uncertainty quantification for 2D/3D anatomical landmark localization using multi-output conformal prediction](https://mlsanity.com/paper/2503.14106/) (2025)
- [Approximating Full Conformal Prediction for Neural Network Regression with Gauss-Newton Influence](https://mlsanity.com/paper/2507.20272/) (2025)
- [Vesicoureteral Reflux Detection with Reliable Probabilistic Outputs](https://mlsanity.com/paper/2312.11355/) (2023)
- [Softmax is not Enough (for Adaptive Conformal Classification)](https://mlsanity.com/paper/2602.19498/) (2026)
- [SPACR: Single-Pass Adaptive Training of Uncertainty-Aware Conformal Regressors](https://mlsanity.com/paper/2606.10734/) (2026)

## Abstract (arXiv)

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.