Deploying deep neural networks (DNNs) on microcontrollers (TinyML) is a common trend to process the increasing amount of sensor data generated at the edge, but in practice, resource and latency constraints make it difficult to find optimal DNN candidates. Neural architecture search (NAS) is an excellent approach to automate this search and can easily be combined with DNN compression techniques commonly used in TinyML. However, many NAS techniques are not only computationally expensive, especially hyperparameter optimization (HPO), but also often focus on optimizing only a single objective, e.g., maximizing accuracy, without considering additional objectives such as memory requirements or computational complexity of a DNN, which are key to making deployment at the edge feasible. In this paper, we propose a novel NAS strategy for TinyML based on multi-objective Bayesian optimization (MOBOpt) and an ensemble of competing parametric policies trained using Augmented Random Search (ARS) reinforcement learning (RL) agents. Our methodology aims at efficiently finding tradeoffs between a DNN's predictive accuracy, memory requirements on a given target system, and computational complexity. Our experiments show that we consistently outperform existing MOBOpt approaches on different datasets and architectures such as ResNet-18 and MobileNetV3.

翻译：在微控制器上部署深度神经网络是处理边缘设备生成的海量传感器数据的普遍趋势，但实践中资源与延迟限制使得寻找最优DNN候选模型变得困难。神经架构搜索是自动化搜索过程的理想方法，可轻松与TinyML常用的DNN压缩技术结合。然而，许多NAS技术不仅计算成本高昂（尤其是超参数优化），且往往仅聚焦于优化单一目标（如最大化准确率），未考虑内存需求或计算复杂度等对边缘部署至关重要的其他目标。本文提出一种基于多目标贝叶斯优化与集成竞争策略的TinyML新型NAS策略，该策略通过增强随机搜索强化学习智能体训练参数化策略集合。我们的方法旨在高效寻找DNN预测准确率、目标系统内存需求及计算复杂度之间的平衡点。实验表明，在ResNet-18和MobileNetV3等不同数据集和架构上，我们的方法持续优于现有MOBOpt方案。