A Flow-Based Generative Model for Rare-Event Simulation
This method addresses rare-event simulation for decision-making in complex stochastic environments, offering an incremental improvement by combining existing techniques like Normalizing Flows and Importance Sampling.
The paper tackles the problem of Monte Carlo sampling overlooking rare but important events in decision-making by presenting a flow-based generative model that simulates samples directly from conditional rare-event distributions, achieving highly accurate estimates of integrals and expectations in high-dimensional settings.
Solving decision problems in complex, stochastic environments is often achieved by estimating the expected outcome of decisions via Monte Carlo sampling. However, sampling may overlook rare, but important events, which can severely impact the decision making process. We present a method in which a Normalizing Flow generative model is trained to simulate samples directly from a conditional distribution given that a rare event occurs. By utilizing Coupling Flows, our model can, in principle, approximate any sampling distribution arbitrarily well. By combining the approximation method with Importance Sampling, highly accurate estimates of complicated integrals and expectations can be obtained. We include several examples to demonstrate how the method can be used for efficient sampling and estimation, even in high-dimensional and rare-event settings. We illustrate that by simulating directly from a rare-event distribution significant insight can be gained into the way rare events happen.