Deep Bayesian Active Learning for Accelerating Stochastic Simulation
This work addresses the challenge of speeding up stochastic simulations for domains like epidemic modeling, though it appears incremental as it builds upon existing Neural Process methods.
The authors tackled the problem of accelerating computationally expensive stochastic simulations by proposing Interactive Neural Process (INP), a deep Bayesian active learning framework, which includes a spatiotemporal surrogate model and a novel acquisition function. The results show that their method outperforms baselines in offline learning and achieves state-of-the-art performance in Bayesian active learning on complex simulators.
Stochastic simulations such as large-scale, spatiotemporal, age-structured epidemic models are computationally expensive at fine-grained resolution. While deep surrogate models can speed up the simulations, doing so for stochastic simulations and with active learning approaches is an underexplored area. We propose Interactive Neural Process (INP), a deep Bayesian active learning framework for learning deep surrogate models to accelerate stochastic simulations. INP consists of two components, a spatiotemporal surrogate model built upon Neural Process (NP) family and an acquisition function for active learning. For surrogate modeling, we develop Spatiotemporal Neural Process (STNP) to mimic the simulator dynamics. For active learning, we propose a novel acquisition function, Latent Information Gain (LIG), calculated in the latent space of NP based models. We perform a theoretical analysis and demonstrate that LIG reduces sample complexity compared with random sampling in high dimensions. We also conduct empirical studies on three complex spatiotemporal simulators for reaction diffusion, heat flow, and infectious disease. The results demonstrate that STNP outperforms the baselines in the offline learning setting and LIG achieves the state-of-the-art for Bayesian active learning.