Latency-Aware Neural Architecture Search with Multi-Objective Bayesian Optimization
By David Eriksson, Pierce I-Jen Chuang, Sam Daulton, Ahmed Aly, Arun Babu, Akshat Shrivastava, Peng Xia, Shicong Zhao, Ganesh Venkatesh, M. Balandat. 2021
21 citations recorded by the source corpus.
When tuning the architecture and hyperparameters of large machine learning models for on-device deployment, it is desirable to understand the optimal trade-offs between on-device latency and model accuracy. In this work, we leverage recent methodological advances in Bayesian optimization over high-dimensional search spaces and multi-objective Bayesian optimization to efficiently explore these trade-offs for a production-scale on-device natural language understanding model at Facebook.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Management Science and Operations Research, Model Architectures
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Carole-Jean Wu
- Bilge Acun
- Michael G. Rabbat
- Kim M. Hazelwood
- Hsien-Hsin S. Lee
- Udit Gupta
- Newsha Ardalani
- Maximilian Balandat
In Computer Vision and Pattern Recognition
- Carole-Jean Wu
- Michael G. Rabbat
- Kim M. Hazelwood
- Bilge Acun
- Hsien-Hsin S. Lee
- Salvatore Candido
- Udit Gupta
- Newsha Ardalani
In Management Science and Operations Research
In Model Architectures
Citations in the corpus
- Sustainable AI: Environmental Implications, Challenges and Opportunities (2021, background): “Beyond model accuracy and timing performance (Joglekar et al., 2020; Song et al., 2020; Tan & Le, 2020; Eriksson et al., 2021), energy and carbon footprint can be directly incorporated into the cost function as optimization objectives (Yang et al.”