Accelerating Stochastic Simulation with Interactive Neural Processes

by   Dongxia Wu, et al.

Stochastic simulations such as large-scale, spatiotemporal, age-structured epidemic models are computationally expensive at fine-grained resolution. We propose Interactive Neural Process (INP), an interactive framework to continuously learn a deep learning surrogate model and accelerate simulation. Our framework is based on the novel integration of Bayesian active learning, stochastic simulation and deep sequence modeling. In particular, we develop a novel spatiotemporal neural process model to mimic the underlying process dynamics. Our model automatically infers the latent process which describes the intrinsic uncertainty of the simulator. This also gives rise to a new acquisition function that can quantify the uncertainty of deep learning predictions. We design Bayesian active learning algorithms to iteratively query the simulator, gather more data, and continuously improve the model. We perform theoretical analysis and demonstrate that our approach reduces sample complexity compared with random sampling in high dimension. Empirically, we demonstrate our framework can faithfully imitate the behavior of a complex infectious disease simulator with a small number of examples, enabling rapid simulation and scenario exploration.



There are no comments yet.


page 1

page 2

page 3

page 4


Deep Bayesian Active Learning with Image Data

Even though active learning forms an important pillar of machine learnin...

Uncertainty Decomposition in Bayesian Neural Networks with Latent Variables

Bayesian neural networks (BNNs) with latent variables are probabilistic ...

Surrogate-based Bayesian Comparison of Computationally Expensive Models: Application to Microbially Induced Calcite Precipitation

Geochemical processes in subsurface reservoirs affected by microbial act...

Decomposition of Uncertainty for Active Learning and Reliable Reinforcement Learning in Stochastic Systems

Bayesian neural networks (BNNs) with latent variables are probabilistic ...

Active Learning for Deep Gaussian Process Surrogates

Deep Gaussian processes (DGPs) are increasingly popular as predictive mo...

Active learning for efficiently training emulators of computationally expensive mathematical models

An emulator is a fast-to-evaluate statistical approximation of a detaile...

Batch-sequential design and heteroskedastic surrogate modeling for delta smelt conservation

Delta smelt is an endangered fish species in the San Francisco estuary t...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.