用多智能体强化学习+置信预测，快速找到适合边缘设备的高效神经网络。
MARCO: Hardware-Aware Neural Architecture Search for Edge Devices with Multi-Agent Reinforcement Learning and Conformal Prediction Filtering
- 分硬件配置与量化两个智能体协同搜索，共享奖励信号优化设计。
- 搜索时间减少3-4倍，精度损失小于0.3%，延迟显著降低。
- 通过置信预测提前剔除劣质架构，保障高质量设计，适合边缘AI部署者。
本文提出MARCO（多智能体强化学习结合置信优化），一种面向资源受限边缘设备的高效神经架构搜索框架。通过显著缩短搜索时间并维持精度，弥合自动化深度神经网络设计与边缘AI部署间的差距。其核心技术在于将多智能体强化学习（MARL）与置信预测（CP）结合，加速软硬件协同设计。不同于需大量预训练的OFA超网方法，MARCO将任务分解为硬件配置代理（HCA）与量化代理（QA），前者优化高层参数，后者在严格内存和延迟预算下确定逐层位宽，采用中心化评价、去中心化执行（CTDE）范式。关键创新是引入校准的置信预测代理模型，提供统计保证（用户定义误覆盖率），在部分训练或硬件仿真前剔除低质量候选架构。该早期过滤大幅缩减搜索空间，同时以高概率保留优质设计。在MNIST、CIFAR-10和CIFAR-100上的实验表明，相比OFA基线，MARCO总搜索时间减少3-4倍，精度保持在基线附近（偏差<0.3%），且推理延迟更低。在MAX78000评估板上的验证确认仿真趋势与实测一致，仿真估计与实测偏差小于5%。
原文摘要 · Abstract (English)
This paper introduces MARCO (Multi-Agent Reinforcement learning with Conformal Optimization), a novel hardware-aware framework for efficient neural architecture search (NAS) targeting resource-constrained edge devices. By significantly reducing search time and maintaining accuracy under strict hardware constraints, MARCO bridges the gap between automated DNN design and CAD for edge AI deployment. MARCO's core technical contribution lies in its unique combination of multi-agent reinforcement learning (MARL) with Conformal Prediction (CP) to accelerate the hardware/software co-design process for deploying deep neural networks. Unlike conventional once-for-all (OFA) supernet approaches that require extensive pretraining, MARCO decomposes the NAS task into a hardware configuration agent (HCA) and a Quantization Agent (QA). The HCA optimizes high-level design parameters, while the QA determines per-layer bit-widths under strict memory and latency budgets using a shared reward signal within a centralized-critic, decentralized-execution (CTDE) paradigm. A key innovation is the integration of a calibrated CP surrogate model that provides statistical guarantees (with a user-defined miscoverage rate) to prune unpromising candidate architectures before incurring the high costs of partial training or hardware simulation. This early filtering drastically reduces the search space while ensuring that high-quality designs are retained with a high probability. Extensive experiments on MNIST, CIFAR-10, and CIFAR-100 demonstrate that MARCO achieves a 3-4x reduction in total search time compared to an OFA baseline while maintaining near-baseline accuracy (within 0.3%). Furthermore, MARCO also reduces inference latency. Validation on a MAX78000 evaluation board confirms that simulator trends hold in practice, with simulator estimates deviating from measured values by less than 5%.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。