No-Regret Gaussian Process Optimization of Time-Varying Functions
This work provides a practical and theoretically grounded solution for sequential optimization of time-varying functions, which is important for applications like online learning and adaptive control.
The paper addresses the challenge of optimizing time-varying black-box functions with noisy evaluations, where no-regret is unattainable under pure bandit feedback. The proposed W-SparQ-GP-UCB algorithm achieves no-regret with a vanishing number of additional queries per iteration, and the authors establish lower bounds proving the method's efficiency.
Sequential optimization of black-box functions from noisy evaluations has been widely studied, with Gaussian Process bandit algorithms such as GP-UCB guaranteeing no-regret in stationary settings. However, for time-varying objectives, no-regret is unattainable under pure bandit feedback unless strong and often unrealistic assumptions are imposed. We propose a novel method for optimizing time-varying rewards in the frequentist setting, where the objective has bounded RKHS norm almost surely. Time variations are captured through uncertainty injection, enabling heteroscedastic Gaussian process regression that adapts past observations to the current time step. As no-regret is unattainable in general in the strict bandit setting, we relax the latter allowing additional queries on previously observed points. Building on sparse inference and the effect of uncertainty injection on regret, we propose W-SparQ-GP-UCB, an online algorithm that achieves no-regret with a vanishing number of additional queries per iteration. To assess the theoretical limits of this approach, we establish a lower bound on the number of additional queries required for no-regret, proving the efficiency of our method. Finally, we provide a comprehensive analysis linking the temporal regime of the function to achievable regret rates, together with upper and lower bounds on the number of additional queries needed in each regime.