TY - GEN
T1 - Optimal policy for deployment of machine learning models on energy-bounded systems
AU - Mirzadeh, Seyed Iman
AU - Ghasemzadeh, Hassan
N1 - Funding Information:
This work was supported in part by the National Science Foundation under grant CNS-1750679. Any opinions, findings, conclusions, or recommendations expressed in this material are those of the authors and do not necessarily reflect the views of the funding organizations. The authors thank Thomas Asaki for helpful discussions.
Publisher Copyright:
© 2020 Inst. Sci. inf., Univ. Defence in Belgrade. All rights reserved.
PY - 2020
Y1 - 2020
N2 - With the recent advances in both machine learning and embedded systems research, the demand to deploy computational models for real-time execution on edge devices has increased substantially. Without deploying computational models on edge devices, the frequent transmission of sensor data to the cloud results in rapid battery draining due to the energy consumption of wireless data transmission. This rapid power dissipation leads to a considerable reduction in the battery lifetime of the system, therefore jeopardizing the real-world utility of smart devices. It is well-established that for difficult machine learning tasks, models with higher performance often require more computation power and thus are not power-efficient choices for deployment on edge devices. However, the trade-offs between performance and power consumption are not well studied. While numerous methods (e.g., model compression) have been developed to obtain an optimal model, these methods focus on improving the efficiency of a “single” model. In an entirely new direction, we introduce an effective method to find a combination of “multiple” models that are optimal in terms of power-efficiency and performance by solving an optimization problem in which both performance and power consumption are taken into account. Experimental results demonstrate that on the ImageNet dataset, we can achieve a 20% energy reduction with only 0.3% accuracy drop compared to Squeeze-and-Excitation Networks. Compared to a pruned neural network for human activity recognition, while consuming 1.7% less energy, our proposed policy achieves 1.3% higher accuracy.
AB - With the recent advances in both machine learning and embedded systems research, the demand to deploy computational models for real-time execution on edge devices has increased substantially. Without deploying computational models on edge devices, the frequent transmission of sensor data to the cloud results in rapid battery draining due to the energy consumption of wireless data transmission. This rapid power dissipation leads to a considerable reduction in the battery lifetime of the system, therefore jeopardizing the real-world utility of smart devices. It is well-established that for difficult machine learning tasks, models with higher performance often require more computation power and thus are not power-efficient choices for deployment on edge devices. However, the trade-offs between performance and power consumption are not well studied. While numerous methods (e.g., model compression) have been developed to obtain an optimal model, these methods focus on improving the efficiency of a “single” model. In an entirely new direction, we introduce an effective method to find a combination of “multiple” models that are optimal in terms of power-efficiency and performance by solving an optimization problem in which both performance and power consumption are taken into account. Experimental results demonstrate that on the ImageNet dataset, we can achieve a 20% energy reduction with only 0.3% accuracy drop compared to Squeeze-and-Excitation Networks. Compared to a pruned neural network for human activity recognition, while consuming 1.7% less energy, our proposed policy achieves 1.3% higher accuracy.
UR - http://www.scopus.com/inward/record.url?scp=85097344240&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85097344240&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85097344240
T3 - IJCAI International Joint Conference on Artificial Intelligence
SP - 3422
EP - 3429
BT - Proceedings of the 29th International Joint Conference on Artificial Intelligence, IJCAI 2020
A2 - Bessiere, Christian
PB - International Joint Conferences on Artificial Intelligence
T2 - 29th International Joint Conference on Artificial Intelligence, IJCAI 2020
Y2 - 1 January 2021
ER -