Searching Toward Pareto-Optimal Device-Aware Neural Architectures
This work addresses the need for efficient neural architectures deployable on diverse devices, from embedded systems to workstations, though it appears incremental as it builds on existing NAS methods.
The paper tackles the problem of Neural Architectural Search (NAS) focusing on optimizing not just accuracy but also device-specific factors like latency and energy, by introducing and evaluating two multi-objective frameworks, MONAS and DPP-Net, which achieve Pareto optimality across various devices.
Recent breakthroughs in Neural Architectural Search (NAS) have achieved state-of-the-art performance in many tasks such as image classification and language understanding. However, most existing works only optimize for model accuracy and largely ignore other important factors imposed by the underlying hardware and devices, such as latency and energy, when making inference. In this paper, we first introduce the problem of NAS and provide a survey on recent works. Then we deep dive into two recent advancements on extending NAS into multiple-objective frameworks: MONAS and DPP-Net. Both MONAS and DPP-Net are capable of optimizing accuracy and other objectives imposed by devices, searching for neural architectures that can be best deployed on a wide spectrum of devices: from embedded systems and mobile devices to workstations. Experimental results are poised to show that architectures found by MONAS and DPP-Net achieves Pareto optimality w.r.t the given objectives for various devices.