# Heteroscedastic Neural Networks for Path Loss Prediction with Link-Specific Uncertainty

arXiv: https://arxiv.org/abs/2511.23243 · HTML: https://mlsanity.com/paper/2511.23243/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 3 of its 14 references that are in the map.
- First posted on arXiv 28 Nov 2025.

## Builds on (most cited first, 3 of 3)

- [Machine Learning-Based Path Loss Modeling with Simplified Features](https://mlsanity.com/paper/2405.10006/) (2024)
- [Site-specific Deep Learning Path Loss Models based on the Method of Moments](https://mlsanity.com/paper/2302.01052/) (2023)
- [Uncertainty Estimation for Path Loss and Radio Metric Models](https://mlsanity.com/paper/2501.06308/) (2025)

## Abstract (arXiv)

Traditional and modern machine learning-based path loss models typically assume a constant prediction variance. We propose a neural network that jointly predicts the mean and link-specific variance by minimizing a Gaussian negative log-likelihood, enabling heteroscedastic uncertainty estimates. We compare shared, partially shared, and independent-parameter architectures using accuracy, calibration, and sharpness metrics on blind test sets from large public RF drive-test datasets. The shared-parameter architecture performs best, achieving an RMSE of 7.4 dB, 95.1 percent coverage for 95 percent prediction intervals, and a mean interval width of 29.6 dB. These uncertainty estimates further support link-specific coverage margins, improve RF planning and interference analyses, and provide effective self-diagnostics of model weaknesses.