GLASSES: Relieving The Myopia Of Bayesian Optimisation
This addresses the limitation of short-sighted planning in global optimization for researchers and practitioners, though it is an incremental improvement over existing non-myopic methods.
The paper tackles the myopia of Bayesian optimization by introducing GLASSES, a non-myopic algorithm that considers dozens of future evaluations through stochastic simulation and Expectation Propagation, leading to substantive performance gains in empirical tests.
We present GLASSES: Global optimisation with Look-Ahead through Stochastic Simulation and Expected-loss Search. The majority of global optimisation approaches in use are myopic, in only considering the impact of the next function value; the non-myopic approaches that do exist are able to consider only a handful of future evaluations. Our novel algorithm, GLASSES, permits the consideration of dozens of evaluations into the future. This is done by approximating the ideal look-ahead loss function, which is expensive to evaluate, by a cheaper alternative in which the future steps of the algorithm are simulated beforehand. An Expectation Propagation algorithm is used to compute the expected value of the loss.We show that the far-horizon planning thus enabled leads to substantive performance gains in empirical tests.