# Ultra-Reliable Risk-Aggregated Sum Rate Maximization via Model-Aided Deep Learning

arXiv: https://arxiv.org/abs/2509.26311 · HTML: https://mlsanity.com/paper/2509.26311/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 28 references that are in the map.
- First posted on arXiv 30 Sep 2025.

## Builds on (most cited first, 10 of 10)

- [Model-Based Deep Learning](https://mlsanity.com/paper/2012.08405/) (2020)
- [Stochastic subgradient method converges on tame functions](https://mlsanity.com/paper/1804.07795/) (2018)
- [Ultra-Reliable and Low-Latency Wireless Communication: Tail, Risk and Scale](https://mlsanity.com/paper/1801.01270/) (2018)
- [Model-Free Learning of Optimal Ergodic Policies in Wireless Systems](https://mlsanity.com/paper/1911.03988/) (2019)
- [On Outage-based Beamforming Design for Dual-Functional Radar-Communication 6G Systems](https://mlsanity.com/paper/2207.04921/) (2022)
- [HPE Transformer: Learning to Optimize Multi-Group Multicast Beamforming Under Nonconvex QoS Constraints](https://mlsanity.com/paper/2402.16081/) (2024)
- [Ultra-Reliable Communication in 5G mmWave Networks: A Risk-Sensitive Approach](https://mlsanity.com/paper/1802.03878/) (2018)
- [Robust and Reliable Stochastic Resource Allocation via Tail Waterfilling](https://mlsanity.com/paper/2305.01053/) (2023)
- [Inexact subgradient methods for semialgebraic functions](https://mlsanity.com/paper/2404.19517/) (2024)
- [Distributionally Robust Power Policies for Wireless Systems under Power Fluctuation Risk](https://mlsanity.com/paper/2412.01187/) (2024)

## Abstract (arXiv)

We consider the problem of maximizing weighted sum rate in a multiple-input single-output (MISO) downlink wireless network with emphasis on user rate reliability. We introduce a novel risk-aggregated formulation of the complex WSR maximization problem, which utilizes the Conditional Value-at-Risk (CVaR) as a functional for enforcing rate (ultra)-reliability over channel fading uncertainty/risk. We establish a WMMSE-like equivalence between the proposed precoding problem and a weighted risk-averse MSE problem, enabling us to design a tailored unfolded graph neural network (GNN) policy function approximation (PFA), named α-Robust Graph Neural Network (αRGNN), trained to maximize lower-tail (CVaR) rates resulting from adverse wireless channel realizations (e.g., deep fading, attenuation). We empirically demonstrate that a trained αRGNN fully eliminates per user deep rate fades, and substantially and optimally reduces statistical user rate variability while retaining adequate ergodic performance.