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 two complex spatiotemporal simulators for reaction diffusion 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.
翻译:大型、 时空、 年龄结构的流行病模型等沙眼模拟模型在精密分辨率下计算成本昂贵。 深代用模型可以加速模拟, 用于随机模拟和积极的学习方法, 是一个探索不足的领域。 我们提出互动神经过程( INP), 深入的Bayesian 积极学习框架, 用于学习深代用模型, 以加速随机模拟。 INP 由两个部分组成, 一个基于神经过程( NP) 家族的随机代用模型, 以及一个用于积极学习的获取功能。 对于代用模型, 我们开发超时神经过程(STNP) 来模拟模拟模拟模拟动力。 对于积极学习, 我们提出一个新的获取功能, 即远程信息增益(LIG), 在基于 NP 模型的潜藏空间中计算。 我们进行理论分析, 并证明LIG 与高维度随机取样相比, 降低样本复杂性。 我们还对两种复杂的神经过程模拟模型模型进行实验性研究, 用于反应扩散和传染性疾病研究。