One Size Does Not Fit All: Quantifying and Exposing the Accuracy-Latency Trade-off in Machine Learning Cloud Service APIs via Tolerance Tiers
| Autor: | Matthew Halpern, Behzad Boroujerdian, Todd W. Mummert, Vijay Janapa Reddi, Evelyn Duesterwald |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
010302 applied physics
FOS: Computer and information sciences Computer Science - Machine Learning Computer Science - Performance Contextual image classification Artificial neural network End user business.industry Computer science Distributed computing Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition Cloud computing 02 engineering and technology 01 natural sciences 020202 computer hardware & architecture Machine Learning (cs.LG) Performance (cs.PF) Software deployment 0103 physical sciences 0202 electrical engineering electronic engineering information engineering Central processing unit Latency (engineering) Architecture business |
| Zdroj: | ISPASS |
| DOI: | 10.48550/arxiv.1906.11307 |
| Popis: | Today's cloud service architectures follow a "one size fits all" deployment strategy where the same service version instantiation is provided to the end users. However, consumers are broad and different applications have different accuracy and responsiveness requirements, which as we demonstrate renders the "one size fits all" approach inefficient in practice. We use a production-grade speech recognition engine, which serves several thousands of users, and an open source computer vision based system, to explain our point. To overcome the limitations of the "one size fits all" approach, we recommend Tolerance Tiers where each MLaaS tier exposes an accuracy/responsiveness characteristic, and consumers can programmatically select a tier. We evaluate our proposal on the CPU-based automatic speech recognition (ASR) engine and cutting-edge neural networks for image classification deployed on both CPUs and GPUs. The results show that our proposed approach provides an MLaaS cloud service architecture that can be tuned by the end API user or consumer to outperform the conventional "one size fits all" approach. Comment: 2019 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS) |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|