Low-Complexity Online Model Selection with Lyapunov Control for Reward Maximization in Stabilized Real-Time Deep Learning Platforms
Do-Hyun Kim, Junseok Kwon, Joongheon Kim · 2018
This paper proposes a low-complexity online model adaptation algorithm which dynamically selects an object detection algorithm among given/implemented algorithms in the system depending on workload-backlog. As well-studied in literature, there exists tradeoff between object detection accuracy and computation time (i.e., delay) because highly accurate algorithms generally take more time due to complicated deep neural network architectures. In our proposed algorithm, the accuracy is reformulated as reward; and the delay is modeled with queue. Based on this queue-based model, Lyapunov control inspired stochastic optimization is utilized for designing time-average reward maximization subject to stability in real-time object detection deep learning platforms. Moreover, our proposed algorithm solves closed-form equation in each model selection interval, thus the proposed algorithm takes low computational complexity. The performance of our proposed algorithm is evaluated via data-intensive real-world implementations under heavy workloads; and is verified that our proposed algorithm works as desired.