Sergey Shirobokov (Imperial)

Black-box optimisation with Local Generative Surrogates (and its application to HEP case)

In the paper we propose a novel method for gradient-based optimisation of black-box simulators using local surrogate models. In fields such as HEP, many processed are modelled with non-differentiable simulators (such as GEANT4). However, often one wants to optimise some parameters of the detector or other apparatus relying on the knowledge from the simulator. To address such cases, we utilise deep generative models to approximate simulator in the local neighbourhood and perform optimisation. In cases, when the optimised parameter space is constrained to a low dimension submanifold, we observe that our method outperforms Bayesian optimisation, numerical optimisation, and REINFORCE-based approaches.