| dc.description.abstract | With the emergence of edge computing, the problem of offloading jobs between an Edge Device (ED) and an Edge Server (ES) received significant attention in the past. Motivated by the fact that an increasing number of applications are using Machine Learning (ML) inference from the data samples collected at the EDs, we study the problem of offloading inference jobs by considering the following novel aspects: 1) in contrast to a typical computational job, the processing time of an inference job depends on the size of the ML model, and 2) recently proposed Deep Neural Networks (DNNs) for resource-constrained devices provide the choice of scaling down the model size by trading off the inference accuracy. Considering that multiple ML models are available at the ED, and a powerful ML model is available at the ES, we formulate an Integer Linear Programming (ILP) problem with the objective of maximizing the total inference accuracy of n data samples at the ED subject to a time constraint T on the makespan. Noting that the problem is NP-hard, we propose an approximation algorithm Accuracy Maximization using LP-Relaxation and Rounding (AMR 2 ) and prove that it results in a makespan at most 2T and achieves a total accuracy that is lower by a small constant from the optimal total accuracy implying that AMR 2 is asymptotically optimal. Further, if the data samples are identical we propose Accuracy Maximization using Dynamic Programming (AMDP), an optimal pseudo-polynomial time algorithm. Furthermore, we extend AMR 2 for the case of multiple ESs, where each ES is equipped with a powerful ML model. As proof of concept, we implemented AMR 2 on a Raspberry Pi, equipped with MobileNets, that is connected to a server equipped with ResNet, and studied the total accuracy and makespan performance of AMR 2 for image classification. | es |
