Monte Carlo Tree Search based Space Transfer for Black-box Optimization
This work addresses the problem of inefficient optimization in computationally expensive black-box settings for researchers and practitioners, offering an incremental improvement over existing search space transfer methods.
The paper tackles the slow convergence of Bayesian optimization in black-box optimization by proposing MCTS-transfer, a method that uses Monte Carlo tree search to adaptively transfer and reconstruct search spaces from similar source tasks, achieving superior performance on synthetic functions, real-world problems, Design-Bench, and hyper-parameter optimization compared to other methods.
Bayesian optimization (BO) is a popular method for computationally expensive black-box optimization. However, traditional BO methods need to solve new problems from scratch, leading to slow convergence. Recent studies try to extend BO to a transfer learning setup to speed up the optimization, where search space transfer is one of the most promising approaches and has shown impressive performance on many tasks. However, existing search space transfer methods either lack an adaptive mechanism or are not flexible enough, making it difficult to efficiently identify promising search space during the optimization process. In this paper, we propose a search space transfer learning method based on Monte Carlo tree search (MCTS), called MCTS-transfer, to iteratively divide, select, and optimize in a learned subspace. MCTS-transfer can not only provide a well-performing search space for warm-start but also adaptively identify and leverage the information of similar source tasks to reconstruct the search space during the optimization process. Experiments on synthetic functions, real-world problems, Design-Bench and hyper-parameter optimization show that MCTS-transfer can demonstrate superior performance compared to other search space transfer methods under different settings. Our code is available at \url{https://github.com/lamda-bbo/mcts-transfer}.