id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
cord-027386-23exaaik	Rao, Vishwas	A Machine-Learning-Based Importance Sampling Method to Compute Rare Event Probabilities	2020-05-25		.txt	text/plain	4292	303	57	title: A Machine-Learning-Based Importance Sampling Method to Compute Rare Event Probabilities We develop a novel computational method for evaluating the extreme excursion probabilities arising from random initialization of nonlinear dynamical systems. The method uses excursion probability theory to formulate a sequence of Bayesian inverse problems that, when solved, yields the biasing distribution. To alleviate the computational cost, we build machine-learning-based surrogates to solve the Bayesian inverse problems that give rise to the biasing distribution. The most commonly used method to determine the probability of rare and extreme events is Monte Carlo simulation (MCS). In this paper, we build on our recent algorithm [25] , which we used to construct an importance biasing distribution (IBD) to accelerate the computation of extreme event probabilities. IS, instead, uses problem-specific information to construct an IBD; computing the rare event probability using the IBD requires fewer samples.	./cache/cord-027386-23exaaik.txt	./txt/cord-027386-23exaaik.txt