No-Regret Algorithms for Safe Bayesian Optimization with Monotonicity Constraints
This addresses the challenge of low cumulative regret in safe optimization for applications like robotics or healthcare, though it is incremental by building on existing safe Bayesian optimization methods.
The paper tackles the problem of safe Bayesian optimization with monotonicity constraints, showing that sublinear regret is achievable when the safety function is monotone in one variable, and extends this to finding near-optimal actions for all inputs.
We consider the problem of sequentially maximizing an unknown function $f$ over a set of actions of the form $(s,\mathbf{x})$, where the selected actions must satisfy a safety constraint with respect to an unknown safety function $g$. We model $f$ and $g$ as lying in a reproducing kernel Hilbert space (RKHS), which facilitates the use of Gaussian process methods. While existing works for this setting have provided algorithms that are guaranteed to identify a near-optimal safe action, the problem of attaining low cumulative regret has remained largely unexplored, with a key challenge being that expanding the safe region can incur high regret. To address this challenge, we show that if $g$ is monotone with respect to just the single variable $s$ (with no such constraint on $f$), sublinear regret becomes achievable with our proposed algorithm. In addition, we show that a modified version of our algorithm is able to attain sublinear regret (for suitably defined notions of regret) for the task of finding a near-optimal $s$ corresponding to every $\mathbf{x}$, as opposed to only finding the global safe optimum. Our findings are supported with empirical evaluations on various objective and safety functions.