Latency-Aware Neural Architecture Search with Multi-Objective Bayesian Optimization

06/22/2021
by   David Eriksson, et al.
10

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.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset