Regret Optimality of GP-UCB

원문 초록

Gaussian Process Upper Confidence Bound (GP-UCB) is one of the most popular methods for optimizing black-box functions with noisy observations, due to its simple structure and superior performance. Its empirical successes lead to a natural, yet unresolved question: Is GP-UCB regret optimal? In this paper, we offer the first generally affirmative answer to this important open question in the Bayesian optimization literature. We establish new upper bounds on both the simple and cumulative regret of GP-UCB when the objective function to optimize admits certain smoothness property. These upper bounds match the known minimax lower bounds (up to logarithmic factors independent of the feasible region's dimensionality) for optimizing functions with the same smoothness. Intriguingly, our findings indicate that, with the same level of exploration, GP-UCB can simultaneously achieve optimality in both simple and cumulative regret. The crux of our analysis hinges on a refined uniform error bound for online estimation of functions in reproducing kernel Hilbert spaces. This error bound, which we derive from empirical process theory, is of independent interest, and its potential applications may reach beyond the scope of this study.