# Outage Performance and Novel Loss Function for an ML-Assisted Resource Allocation: An Exact Analytical Framework

arXiv: https://arxiv.org/abs/2305.09739 · HTML: https://mlsanity.com/paper/2305.09739/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 65 references that are in the map.
- First posted on arXiv 16 May 2023.

## Builds on (most cited first, 15 of 15)

- [Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) Network](https://mlsanity.com/paper/1808.03314/) (2018)
- [Deep Long-Tailed Learning: A Survey](https://mlsanity.com/paper/2110.04596/) (2021)
- [DeepMIMO: A Generic Deep Learning Dataset for Millimeter Wave and Massive MIMO Applications](https://mlsanity.com/paper/1902.06435/) (2019)
- [Deep Learning for mmWave Beam and Blockage Prediction Using Sub-6GHz Channels](https://mlsanity.com/paper/1910.02900/) (2019)
- [High Dimensional Channel Estimation Using Deep Generative Networks](https://mlsanity.com/paper/2006.13494/) (2020)
- [Vision-Aided 6G Wireless Communications: Blockage Prediction and Proactive Handoff](https://mlsanity.com/paper/2102.09527/) (2021)
- [Millimeter Wave Base Stations with Cameras: Vision Aided Beam and Blockage Prediction](https://mlsanity.com/paper/1911.06255/) (2019)
- [Deep Learning for TDD and FDD Massive MIMO: Mapping Channels in Space and Frequency](https://mlsanity.com/paper/1905.03761/) (2019)
- [6G White Paper on Machine Learning in Wireless Communication Networks](https://mlsanity.com/paper/2004.13875/) (2020)
- [Deep Learning Power Allocation in Massive MIMO](https://mlsanity.com/paper/1812.03640/) (2018)
- [Machine Learning for Reliable mmWave Systems: Blockage Prediction and Proactive Handoff](https://mlsanity.com/paper/1807.02723/) (2018)
- [Next Generation Terahertz Communications: A Rendezvous of Sensing, Imaging, and Localization](https://mlsanity.com/paper/1909.10462/) (2019)
- [Prediction of mmWave/THz Link Blockages through Meta-Learning and Recurrent Neural Networks](https://mlsanity.com/paper/2106.07442/) (2021)
- [AI-Based Channel Prediction in D2D Links: An Empirical Validation](https://mlsanity.com/paper/2206.08346/) (2022)
- [Unsupervised Deep Learning for Ultra-reliable and Low-latency Communications](https://mlsanity.com/paper/1905.13014/) (2019)

## Built on by (most cited first, 1 of 1)

- [To Trust or Not to Trust: On Calibration in ML-based Resource Allocation for Wireless Networks](https://mlsanity.com/paper/2507.17494/) (2025)

## Abstract (arXiv)

We introduce a novel loss function to minimize the outage probability of an ML-based resource allocation system. A single-user multi-resource greedy allocation strategy constitutes our application scenario, for which an ML binary classification predictor assists in selecting a resource satisfying the established outage criterium. While other resource allocation policies may be suitable, they are not the focus of our study. Instead, our primary emphasis is on theoretically developing this loss function and leveraging it to train an ML model to address the outage probability challenge. With no access to future channel state information, this predictor foresees each resource's likely future outage status. When the predictor encounters a resource it believes will be satisfactory, it allocates it to the user. Our main result establishes exact and asymptotic expressions for this system's outage probability. These expressions reveal that focusing solely on the optimization of the per-resource outage probability conditioned on the ML predictor recommending resource allocation (a strategy that appears to be most appropriate) may produce inadequate predictors that reject every resource. They also reveal that focusing on standard metrics, like precision, false-positive rate, or recall, may not produce optimal predictors. With our result, we formulate a theoretically optimal, differentiable loss function to train our predictor. We then compare predictors trained using this and traditional loss functions namely, binary cross-entropy (BCE), mean squared error (MSE), and mean absolute error (MAE). In all scenarios, predictors trained using our novel loss function provide superior outage probability performance. Moreover, in some cases, our loss function outperforms predictors trained with BCE, MAE, and MSE by multiple orders of magnitude.