DeepAI
Log In Sign Up

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

page 1

page 2

page 3

page 4

09/22/2021

Multi-Objective Bayesian Optimization over High-Dimensional Search Spaces

The ability to optimize multiple competing objective functions with high...
10/13/2022

Computer-Aided Multi-Objective Optimization in Small Molecule Discovery

Molecular discovery is a multi-objective optimization problem that requi...
06/10/2021

A multi-objective perspective on jointly tuning hardware and hyperparameters

In addition to the best model architecture and hyperparameters, a full A...
07/13/2022

Dynamic Selection of Perception Models for Robotic Control

Robotic perception models, such as Deep Neural Networks (DNNs), are beco...
10/13/2015

UAVs using Bayesian Optimization to Locate WiFi Devices

We address the problem of localizing non-collaborative WiFi devices in a...