OpenBox: A Generalized Black-box Optimization Service

OpenBox is an efficient and generalized blackbox optimization (BBO) system, which supports the following characteristics: 1) BBO with multiple objectives and constraints, 2) BBO with transfer learning, 3) BBO with distributed parallelization, 4) BBO with multi-fidelity acceleration and 5) BBO with early stops. The design of OpenBox follows the following principles: 1) Ease of use: Minimal user effort, and user-friendly visualization for tracking and managing BBO tasks. 2) Consistent performance: Host state-of-the-art optimization algorithms; Choose the proper algorithm automatically. 3) Resource-aware management: Give cost model-based advice to users, e.g., minimal workers or time-budget. 4) Scalability: Scale to dimensions on the number of input variables, objectives, tasks, trials, and parallel evaluations. 5) High efficiency: Effective use of parallel resources, system optimization with transfer-learning and multi-fidelities, etc. 6) Fault tolerance, extensibility, and data privacy protection.