Scalable Global Optimization via Local Bayesian Optimization

10/03/2019
by   David Eriksson, et al.
0

Bayesian optimization has recently emerged as a popular method for the sample-efficient optimization of expensive black-box functions. However, the application to high-dimensional problems with several thousand observations remains challenging, and on difficult problems Bayesian optimization is often not competitive with other paradigms. In this paper we take the view that this is due to the implicit homogeneity of the global probabilistic models and an overemphasized exploration that results from global acquisition. This motivates the design of a local probabilistic approach for global optimization of large-scale high-dimensional problems. We propose the TuRBO algorithm that fits a collection of local models and performs a principled global allocation of samples across these models via an implicit bandit approach. A comprehensive evaluation demonstrates that TuRBO outperforms state-of-the-art methods from machine learning and operations research on problems spanning reinforcement learning, robotics, and the natural sciences.

READ FULL TEXT
research
02/20/2020

Scalable Constrained Bayesian Optimization

The global optimization of a high-dimensional black-box function under b...
research
12/09/2016

Advancing Bayesian Optimization: The Mixed-Global-Local (MGL) Kernel and Length-Scale Cool Down

Bayesian Optimization (BO) has become a core method for solving expensiv...
research
10/02/2022

Robust Bayesian optimization with reinforcement learned acquisition functions

In Bayesian optimization (BO) for expensive black-box optimization tasks...
research
11/10/2021

Searching in the Forest for Local Bayesian Optimization

Because of its sample efficiency, Bayesian optimization (BO) has become ...
research
03/02/2015

Bayesian Optimization of Text Representations

When applying machine learning to problems in NLP, there are many choice...
research
02/14/2023

Scalable Bayesian optimization with high-dimensional outputs using randomized prior networks

Several fundamental problems in science and engineering consist of globa...
research
04/22/2023

Increasing the Scope as You Learn: Adaptive Bayesian Optimization in Nested Subspaces

Recent advances have extended the scope of Bayesian optimization (BO) to...

Please sign up or login with your details

Forgot password? Click here to reset