Relaxing the Additivity Constraints in Decentralized No-Regret High-Dimensional Bayesian Optimization
This work addresses the problem of high-dimensional optimization for researchers and practitioners in machine learning, offering an incremental improvement by relaxing assumptions in decentralized BO.
The paper tackles the challenge of scaling Bayesian Optimization (BO) to high-dimensional spaces by relaxing restrictive additive structure assumptions and addressing over-exploration in decentralized BO, resulting in the DuMBO algorithm that achieves competitive performance, particularly with high-dimensional factors.
Bayesian Optimization (BO) is typically used to optimize an unknown function $f$ that is noisy and costly to evaluate, by exploiting an acquisition function that must be maximized at each optimization step. Even if provably asymptotically optimal BO algorithms are efficient at optimizing low-dimensional functions, scaling them to high-dimensional spaces remains an open problem, often tackled by assuming an additive structure for $f$. By doing so, BO algorithms typically introduce additional restrictive assumptions on the additive structure that reduce their applicability domain. This paper contains two main contributions: (i) we relax the restrictive assumptions on the additive structure of $f$ without weakening the maximization guarantees of the acquisition function, and (ii) we address the over-exploration problem for decentralized BO algorithms. To these ends, we propose DuMBO, an asymptotically optimal decentralized BO algorithm that achieves very competitive performance against state-of-the-art BO algorithms, especially when the additive structure of $f$ comprises high-dimensional factors.