# Learning-Accelerated Joint AP/RIS Optimization for Low-Latency Indoor mmWave XR Networks

DevFeed: [Learning-Accelerated Joint AP/RIS Optimization for Low-Latency Indoor mmWave XR Networks](<https://devfeed.tech/articles/learning-accelerated-joint-ap-ris-optimization-for-low-latency-indoor-mmwave-xr-networks-101666.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.33945>)

Author: Ali Elghariani, Mohammed Elbamby, Anis Elgabli

Published: 2026-10-27T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Networking](<https://devfeed.tech/sources/arxiv-networking.md>)

Topics: [AI Networking](<https://devfeed.tech/topics/ai-networking.md>), [Learning](<https://devfeed.tech/topics/learning.md>)

Tags: [accelerated](<https://devfeed.tech/tags/accelerated.md>), [access-points](<https://devfeed.tech/tags/access-points.md>), [applications](<https://devfeed.tech/tags/applications.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [channel](<https://devfeed.tech/tags/channel.md>), [controller](<https://devfeed.tech/tags/controller.md>), [convergence](<https://devfeed.tech/tags/convergence.md>), [convex](<https://devfeed.tech/tags/convex.md>), [critical](<https://devfeed.tech/tags/critical.md>), [cs-ni](<https://devfeed.tech/tags/cs-ni.md>), [deployments](<https://devfeed.tech/tags/deployments.md>), [design](<https://devfeed.tech/tags/design.md>), [dimension](<https://devfeed.tech/tags/dimension.md>), [extended-reality](<https://devfeed.tech/tags/extended-reality.md>), [latency](<https://devfeed.tech/tags/latency.md>), [learning](<https://devfeed.tech/tags/learning.md>), [low-latency](<https://devfeed.tech/tags/low-latency.md>), [mmwave](<https://devfeed.tech/tags/mmwave.md>), [networks](<https://devfeed.tech/tags/networks.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [ris](<https://devfeed.tech/tags/ris.md>)

## AI overview

The paper jointly optimizes access point precoders and reconfigurable intelligent surface phase shifts for indoor mmWave XR, where multiple APs serve users on a shared channel under centralized control. Its alternating optimization method monotonically improves sum rate and converges to a coordinate-wise stationary point, but can be too slow for real-time use as system size grows. A supervised learning-assisted approach uses AO-generated solutions to reduce the number of iterations. Simulations report near-optimal performance with substantially fewer AO iterations; the evidence provided does not quantify the speedup.

## Source excerpt

arXiv:2610.33945v1 Announce Type: new Abstract: This paper studies a reconfigurable intelligent surface (RIS)-assisted indoor architecture for extended reality (XR) applications, where multiple access points (APs) simultaneously serve multiple users over a shared frequency channel under a centralized AP controller. We formulate a non-convex sum-rate maximization problem with coupled AP precoders and RIS phase shifts, and develop a centralized alternating optimization (AO) framework for joint design. We rigorously prove that the proposed AO guarantees monotonic improvement of the sum rate that converges to a coordinate-wise stationary point, despite the non-convexity of the resulting subproblems. Although AO provides reliable performance, its iterative nature limits real-time applicability as the system dimension grows. To overcome this limitation, we propose a supervised learning-assisted approach that leverages AO-generated solutions to significantly accelerate convergence. Simulation results demonstrate that the proposed framework achieves near-optimal performance with substantially fewer AO iterations, which makes it well-suited for latency-critical RIS-assisted XR deployments.