mlsanityData to 14 Oct 2026

DIFFRACT: Neuralized Utility Maximization for Wireless Networks by Differentiable Programming

arXiv 2606.07114 ↗First posted 5 Jun 2026cs.NI cs.AI cs.ITcited by 0

Not on the map. Why?

Abstract (arXiv)

Next-generation wireless networks, including satellite-to-Open RAN systems, demand agile and intelligent resource management capable of handling dynamic multi-user interference under stochastic quality of service constraints. This paper introduces DIFFRACT, a neuralized utility maximization framework that leverages differentiable programming to integrate deep learning with optimization in wireless networks. Central to our approach is the exploitation of the mathematical structure of standard interference functions, which are foundational in wireless power control. By developing a duality theory for these functions, we map iterative interference management algorithms into differentiable neural network architectures via algorithm unrolling. This enables distributed, end-to-end gradient-based learning at the network edge, supporting real-time adaptation to interference in both terrestrial and non-terrestrial environments. DIFFRACT allows for scalable and robust utility maximization by modeling complex channel dynamics and leveraging the expressiveness of differentiable models. Experimental results confirm the framework's theoretical soundness and practical effectiveness for next-generation wireless systems.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 17 of its 50 references that are in the map. First posted on arXiv 5 Jun 2026.

Builds on

17 of 50 references.

References · 17

  1. 2021Convex optimizationcited by 2,515
  2. 2019Differentiable Convex Optimization Layerscited by 465
  3. 2019Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processingcited by 421
  4. 2017An Introduction to Deep Learning for the Physical Layercited by 233
  5. 2020Monotone operator equilibrium networkscited by 100
  6. 2017Learning to Optimize: Training Deep Neural Networks for Wireless Resource Managementcited by 96
  7. 2023Sionna RT: Differentiable Ray Tracing for Radio Propagation Modelingcited by 62
  8. 2022Model-Based Deep Learning: On the Intersection of Deep Learning and Optimizationcited by 50
  9. 2024The Elements of Differentiable Programmingcited by 43
  10. 2019Artificial Intelligence-Enabled Cellular Networks: A Critical Path to Beyond-5G and 6Gcited by 25
  11. 2023Learning Radio Environments by Differentiable Ray Tracingcited by 23
  12. 2020Learning Convex Optimization Modelscited by 16
5 more
  1. 2020Fixed Point Strategies in Data Sciencecited by 16
  2. 2024Learning to optimize: A tutorial for continuous and mixed-integer optimizationcited by 8
  3. 2020Differentiating through Log-Log Convex Programscited by 7
  4. 2021Space-Terrestrial Integrated Internet of Things: Challenges and Opportunitiescited by 4
  5. 2022Space-Terrestrial Cooperation Over Spatially Correlated Channels Relying on Imperfect Channel Estimates: Uplink Performance Analysis and Optimizationcited by 1

Built on by

Not cited yet.