Constrained Bayesian Optimization with Noisy Experiments
This addresses the challenge of efficiently optimizing parameters in noisy real-world experiments, such as those at Facebook, though it is incremental as it builds on existing Bayesian optimization techniques.
The paper tackled the problem of Bayesian optimization degrading under high noise in randomized experiments, and developed a method for noisy, constrained optimization that outperforms existing approaches in simulations and real-world tests at Facebook.
Randomized experiments are the gold standard for evaluating the effects of changes to real-world systems. Data in these tests may be difficult to collect and outcomes may have high variance, resulting in potentially large measurement error. Bayesian optimization is a promising technique for efficiently optimizing multiple continuous parameters, but existing approaches degrade in performance when the noise level is high, limiting its applicability to many randomized experiments. We derive an expression for expected improvement under greedy batch optimization with noisy observations and noisy constraints, and develop a quasi-Monte Carlo approximation that allows it to be efficiently optimized. Simulations with synthetic functions show that optimization performance on noisy, constrained problems outperforms existing methods. We further demonstrate the effectiveness of the method with two real-world experiments conducted at Facebook: optimizing a ranking system, and optimizing server compiler flags.