Knowledge Gradient for Multi-Objective Bayesian Optimization with Decoupled Evaluations
This work addresses the challenge of reducing evaluation costs in multi-objective optimization for applications like engineering design or hyperparameter tuning, though it is incremental as it builds on existing scalarization and knowledge gradient methods.
The paper tackles the problem of efficiently learning Pareto fronts in multi-objective Bayesian optimization when objectives can be evaluated separately with different costs, proposing a scalarization-based knowledge gradient acquisition function that accounts for these costs. The result shows asymptotic consistency and empirical performance comparable to state-of-the-art methods, with significant improvements over approaches that always evaluate both objectives.
Multi-objective Bayesian optimization aims to find the Pareto front of trade-offs between a set of expensive objectives while collecting as few samples as possible. In some cases, it is possible to evaluate the objectives separately, and a different latency or evaluation cost can be associated with each objective. This decoupling of the objectives presents an opportunity to learn the Pareto front faster by avoiding unnecessary, expensive evaluations. We propose a scalarization based knowledge gradient acquisition function which accounts for the different evaluation costs of the objectives. We prove asymptotic consistency of the estimator of the optimum for an arbitrary, D-dimensional, real compact search space and show empirically that the algorithm performs comparably with the state of the art and significantly outperforms versions which always evaluate both objectives.