# Quantifying Point-Prediction Uncertainty in Neural Networks via Residual Estimation with an I/O Kernel

arXiv: https://arxiv.org/abs/1906.00588 · HTML: https://mlsanity.com/paper/1906.00588/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jun 2019.

## Built on by (most cited first, 19 of 19)

- [Image-to-Image Regression with Distribution-Free Uncertainty Quantification and Applications in Imaging](https://mlsanity.com/paper/2202.05265/) (2022)
- [Quantifying Uncertainty in Deep Spatiotemporal Forecasting](https://mlsanity.com/paper/2105.11982/) (2021)
- [Uncertainty Quantification Metrics for Deep Regression](https://mlsanity.com/paper/2405.04278/) (2024)
- [DeepGLEAM: A hybrid mechanistic and deep learning model for COVID-19 forecasting](https://mlsanity.com/paper/2102.06684/) (2021)
- [A Novel Regression Loss for Non-Parametric Uncertainty Optimization](https://mlsanity.com/paper/2101.02726/) (2021)
- [Uncertainty-Aware Boosted Ensembling in Multi-Modal Settings](https://mlsanity.com/paper/2104.10715/) (2021)
- [CUE: An Uncertainty Interpretation Framework for Text Classifiers Built on Pre-Trained Language Models](https://mlsanity.com/paper/2306.03598/) (2023)
- [EVOTER: Evolution of Transparent Explainable Rule-sets](https://mlsanity.com/paper/2204.10438/) (2022)
- [Beyond the Norms: Detecting Prediction Errors in Regression Models](https://mlsanity.com/paper/2406.06968/) (2024)
- [Scheduling Planting Time Through Developing an Optimization Model and Analysis of Time Series Growing Degree Units](https://mlsanity.com/paper/2207.00745/) (2022)
- [Learning Mixture Structure on Multi-Source Time Series for Probabilistic Forecasting](https://mlsanity.com/paper/2302.11078/) (2023)
- [Discovering Effective Policies for Land-Use Planning with Neuroevolution](https://mlsanity.com/paper/2311.12304/) (2023)
- [Scalable Bayesian Monte Carlo: fast uncertainty estimation beyond deep ensembles](https://mlsanity.com/paper/2505.13585/) (2025)
- [Uncertainty Surrogates for Deep Learning](https://mlsanity.com/paper/2104.08147/) (2021)
- [Evaluating Point-Prediction Uncertainties in Neural Networks for Drug Discovery](https://mlsanity.com/paper/2210.17043/) (2022)
- [Quantification of Predictive Uncertainty via Inference-Time Sampling](https://mlsanity.com/paper/2308.01731/) (2023)
- [Unlocking the Potential of Global Human Expertise](https://mlsanity.com/paper/2411.00156/) (2024)
- [Semantic-Aware Gaussian Process Calibration with Structured Layerwise Kernels for Deep Neural Networks](https://mlsanity.com/paper/2507.15987/) (2025)
- [Adaptive Individual Uncertainty under Out-Of-Distribution Shift with Expert-Routed Conformal Prediction](https://mlsanity.com/paper/2510.15233/) (2025)

## Abstract (arXiv)

Neural Networks (NNs) have been extensively used for a wide spectrum of real-world regression tasks, where the goal is to predict a numerical outcome such as revenue, effectiveness, or a quantitative result. In many such tasks, the point prediction is not enough: the uncertainty (i.e. risk or confidence) of that prediction must also be estimated. Standard NNs, which are most often used in such tasks, do not provide uncertainty information. Existing approaches address this issue by combining Bayesian models with NNs, but these models are hard to implement, more expensive to train, and usually do not predict as accurately as standard NNs. In this paper, a new framework (RIO) is developed that makes it possible to estimate uncertainty in any pretrained standard NN. The behavior of the NN is captured by modeling its prediction residuals with a Gaussian Process, whose kernel includes both the NN's input and its output. The framework is evaluated in twelve real-world datasets, where it is found to (1) provide reliable estimates of uncertainty, (2) reduce the error of the point predictions, and (3) scale well to large datasets. Given that RIO can be applied to any standard NN without modifications to model architecture or training pipeline, it provides an important ingredient for building real-world NN applications.