A Flexible Framework for Multi-Objective Bayesian Optimization using Random Scalarizations
This work addresses the need for flexible and efficient optimization in real-world applications where practitioners require Pareto optimal points in specific subsets, offering an incremental improvement over traditional methods.
The paper tackles the problem of multi-objective Bayesian optimization by proposing a random scalarization strategy to sample from specific regions of the Pareto front, achieving sublinear regret and demonstrating superior performance in flexibility and computational efficiency.
Many real world applications can be framed as multi-objective optimization problems, where we wish to simultaneously optimize for multiple criteria. Bayesian optimization techniques for the multi-objective setting are pertinent when the evaluation of the functions in question are expensive. Traditional methods for multi-objective optimization, both Bayesian and otherwise, are aimed at recovering the Pareto front of these objectives. However, in certain cases a practitioner might desire to identify Pareto optimal points only in a subset of the Pareto front due to external considerations. In this work, we propose a strategy based on random scalarizations of the objectives that addresses this problem. Our approach is able to flexibly sample from desired regions of the Pareto front and, computationally, is considerably cheaper than most approaches for MOO. We also study a notion of regret in the multi-objective setting and show that our strategy achieves sublinear regret. We experiment with both synthetic and real-life problems, and demonstrate superior performance of our proposed algorithm in terms of the flexibility and regret.