A Flow-Based Generative Model for Rare-Event Simulation

Understand

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.