Serving unseen deep learning model with near-optimal configurations: A fast adaptive search approach
Last updated
Was this helpful?
Last updated
Was this helpful?
Presented in .
Authors: Yuewen Wu, Heng Wu, Diaohan Luo, Yuanjia Xu, Yi Hu, Wenbo Zhang, Hua Zhong, Institute of Software, Chinese Academy of Sciences
Code:
This paper presents Falcon, a novel configuration recommender system that can quickly adapt to unseen DL models.
There exists a cold start problem when searching a configuration of DL models.
Some Key Operators (KOPs) can be used to estimate the performance of DL models.
The resource sensitivity can be represented by four typical Key Operator Resource Curves (KOP-RCs), including Slope, Convex, Concave, and Plane.
A DL model can be characterized by its KOPs and corresponding KOP-RCs.
Use a combination of Monte Carlo Tree Search and Bayesian Optimization (MCTS-BO) to search the configurations.
Compared to Morphling.