A Nonmyopic Approach to Cost-Constrained Bayesian Optimization
This addresses cost efficiency in BO for applications like hyperparameter tuning and clinical trials, but it is incremental as it builds on existing BO methods with a new cost-aware approach.
The paper tackles the problem of Bayesian optimization (BO) where evaluation costs vary across the search space, by formulating it as a constrained Markov decision process (CMDP) and developing an efficient rollout approximation to optimize cost efficiency, validated on hyperparameter optimization and sensor set selection tasks.
Bayesian optimization (BO) is a popular method for optimizing expensive-to-evaluate black-box functions. BO budgets are typically given in iterations, which implicitly assumes each evaluation has the same cost. In fact, in many BO applications, evaluation costs vary significantly in different regions of the search space. In hyperparameter optimization, the time spent on neural network training increases with layer size; in clinical trials, the monetary cost of drug compounds vary; and in optimal control, control actions have differing complexities. Cost-constrained BO measures convergence with alternative cost metrics such as time, money, or energy, for which the sample efficiency of standard BO methods is ill-suited. For cost-constrained BO, cost efficiency is far more important than sample efficiency. In this paper, we formulate cost-constrained BO as a constrained Markov decision process (CMDP), and develop an efficient rollout approximation to the optimal CMDP policy that takes both the cost and future iterations into account. We validate our method on a collection of hyperparameter optimization problems as well as a sensor set selection application.