Bayes-Split-Edge: Bayesian Optimization for Constrained Collaborative Inference in Wireless Edge Systems

2025-10-27

AI Summary

This work addresses the collaborative inference optimization problem for resource-constrained wireless edge devices (e.g., AR/VR headsets) under strict latency and energy constraints. We propose Bayes-Split-Edge, a framework that jointly optimizes neural network partitioning points and wireless transmission power to enable efficient inference collaboration between edge devices and remote servers. Our key contribution is a novel hybrid acquisition function for Bayesian optimization that simultaneously balances utility, sampling efficiency, and constraint violation penalties—significantly improving search quality under stringent constraints. Evaluated on VGG19 and ResNet101 over realistic mobile channel traces, Bayes-Split-Edge converges within ≤20 function evaluations, reducing evaluation cost by 2.4× compared to standard Bayesian optimization. It consistently outperforms baselines including CMA-ES and PPO, achieving performance close to exhaustive search while maintaining practical feasibility for real-time edge deployment.

Technology Category

• Search and Optimization: Learning to Search
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Machine Learning: Learning on the Edge & Model Compression

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines

Abstract

Mobile edge devices (e.g., AR/VR headsets) typically need to complete timely inference tasks while operating with limited on-board computing and energy resources. In this paper, we investigate the problem of collaborative inference in wireless edge networks, where energy-constrained edge devices aim to complete inference tasks within given deadlines. These tasks are carried out using neural networks, and the edge device seeks to optimize inference performance under energy and delay constraints. The inference process can be split between the edge device and an edge server, thereby achieving collaborative inference over wireless networks. We formulate an inference utility optimization problem subject to energy and delay constraints, and propose a novel solution called Bayes-Split-Edge, which leverages Bayesian optimization for collaborative split inference over wireless edge networks. Our solution jointly optimizes the transmission power and the neural network split point. The Bayes-Split-Edge framework incorporates a novel hybrid acquisition function that balances inference task utility, sample efficiency, and constraint violation penalties. We evaluate our approach using the VGG19 model on the ImageNet-Mini dataset, and Resnet101 on Tiny-ImageNet, and real-world mMobile wireless channel datasets. Numerical results demonstrate that Bayes-Split-Edge achieves up to 2.4x reduction in evaluation cost compared to standard Bayesian optimization and achieves near-linear convergence. It also outperforms several baselines, including CMA-ES, DIRECT, exhaustive search, and Proximal Policy Optimization (PPO), while matching exhaustive search performance under tight constraints. These results confirm that the proposed framework provides a sample-efficient solution requiring maximum 20 function evaluations and constraint-aware optimization for wireless split inference in edge computing systems.

Problem

• Optimizing neural network split inference under energy constraints
• Jointly optimizing transmission power and network split points
• Balancing inference utility with wireless delay constraints

Innovation

• Bayesian optimization for wireless edge collaborative inference
• Jointly optimizes transmission power and neural split point
• Hybrid acquisition function balances utility and constraints