BILBO: BILevel Bayesian Optimization
This addresses sample inefficiency and suboptimality in noisy, constrained, derivative-free bilevel optimization, which is prevalent in real-world applications, representing a novel method for a known bottleneck.
The paper tackles bilevel optimization problems, which are challenging due to constraints from optimal lower-level solutions, by introducing BILBO, a Bayesian optimization algorithm that simultaneously optimizes both levels without repeated lower-level optimization, achieving theoretical sublinear regret bounds and empirical performance on synthetic and real-world problems.
Bilevel optimization is characterized by a two-level optimization structure, where the upper-level problem is constrained by optimal lower-level solutions, and such structures are prevalent in real-world problems. The constraint by optimal lower-level solutions poses significant challenges, especially in noisy, constrained, and derivative-free settings, as repeating lower-level optimizations is sample inefficient and predicted lower-level solutions may be suboptimal. We present BILevel Bayesian Optimization (BILBO), a novel Bayesian optimization algorithm for general bilevel problems with blackbox functions, which optimizes both upper- and lower-level problems simultaneously, without the repeated lower-level optimization required by existing methods. BILBO samples from confidence-bounds based trusted sets, which bounds the suboptimality on the lower level. Moreover, BILBO selects only one function query per iteration, where the function query selection strategy incorporates the uncertainty of estimated lower-level solutions and includes a conditional reassignment of the query to encourage exploration of the lower-level objective. The performance of BILBO is theoretically guaranteed with a sublinear regret bound for commonly used kernels and is empirically evaluated on several synthetic and real-world problems.