Exploration Query
A query strategy for Bayesian optimization that selects points maximizing spatial coverage or reducing global uncertainty, such as the point maximizing the posterior standard deviation. It compensates for the shortcomings of acquisition functions optimized for cumulative regret in terms of final output quality.
Timeline (last 90 days)
The exploration strategy proposed in this study is: in any Bayesian optimization procedure, occasionally replace the acquisition query with an exploration query.
This exploration query replacement scheme does not change the main structure of the original algorithm and can be seamlessly integrated into existing Bayesian optimization frameworks.
On synthetic benchmarks, a hyperparameter optimization task and a control task, after introducing the exploration strategy, the final recommendation quality of existing Bayesian optimization algorithms was improved in all cases.
The replacement frequency of the exploration queries and the optimal insertion phase may still leave room for insufficient discussion in this study.
All Facts (4)
The exploration strategy proposed in this study is: in any Bayesian optimization procedure, occasionally replace the acquisition query with an exploration query.
50%UnverifiedThis exploration query replacement scheme does not change the main structure of the original algorithm and can be seamlessly integrated into existing Bayesian optimization frameworks.
50%UnverifiedOn synthetic benchmarks, a hyperparameter optimization task and a control task, after introducing the exploration strategy, the final recommendation quality of existing Bayesian optimization algorithms was improved in all cases.
50%UnverifiedThe replacement frequency of the exploration queries and the optimal insertion phase may still leave room for insufficient discussion in this study.
50%