AMC：面向移动设备模型压缩与加速的 AutoML
AMC: AutoML for Model Compression and Acceleration on Mobile Devices
AI总结：
提出 AMC，利用强化学习自动搜索模型压缩策略，在 VGG-16 与 MobileNet 上实现更高压缩率、更低延迟且准确率损失极小。
摘要：
模型压缩是在计算资源有限、功耗预算紧张的移动设备上高效部署神经网络模型的关键技术。传统模型压缩技术依赖手工启发式方法和基于规则的策略，需要领域专家探索庞大的设计空间，以在模型大小、速度和准确率之间进行权衡，这通常次优且耗时。本文提出用于模型压缩的 AutoML（AutoML for Model Compression，AMC），利用强化学习提供模型压缩策略。这种基于学习的压缩策略优于传统的基于规则的压缩策略，具有更高的压缩率，能更好地保持准确率，并免除人工劳动。在 FLOPs 减少 4 倍的条件下，对于 ImageNet 上的 VGG-16，我们取得的准确率比手工模型压缩策略高 2.7%。我们将这种自动化的“一键式”压缩流程应用于 MobileNet，在 Android 手机上测得的推理延迟实现 1.81 倍加速，在 Titan XP GPU 上实现 1.43 倍加速，而 ImageNet Top-1 准确率仅损失 0.1%。
英文摘要：
Model compression is a critical technique to efficiently deploy neural network models on mobile devices which have limited computation resources and tight power budgets. Conventional model compression techniques rely on hand-crafted heuristics and rule-based policies that require domain experts to explore the large design space trading off among model size, speed, and accuracy, which is usually sub-optimal and time-consuming. In this paper, we propose AutoML for Model Compression (AMC) which leverage reinforcement learning to provide the model compression policy. This learning-based compression policy outperforms conventional rule-based compression policy by having higher compression ratio, better preserving the accuracy and freeing human labor. Under 4x FLOPs reduction, we achieved 2.7% better accuracy than the handcrafted model compression policy for VGG-16 on ImageNet. We applied this automated, push-the-button compression pipeline to MobileNet and achieved 1.81x speedup of measured inference latency on an Android phone and 1.43x speedup on the Titan XP GPU, with only 0.1% loss of ImageNet Top-1 accuracy.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
