Important sampling in high dimensions

375 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Rare event estimation with sequential directional importance sampling (2022, methodology): “Existing methods in the literature can be categorized into four types: approximate analytical methods [2, 3], moment-based methods [4-8], surrogate-assisted methods [9-13] and numerical simulation methods [14-16].”
MCMC algorithms for Subset Simulation (2015, methodology): “𝑓 in several applications of Subset Simulation (Au & Beck 2001, Au & Beck 2003b).”
Uncertainty analysis of complex structural systems (2009, background): “Moreover, in [42] the challenges related with high-dimensional reliability problems, addressed in [35, 43], are described in detail.”
Dense reinforcement learning for safety validation of autonomous vehicles (2023, background): “…MDP problem associated with rare events and high-dimensional variables remains a highly challenging problem, and most existing importance sampling-based methods suffer from the curse of dimensionality 40 , where the estimation variance would increase exponentially with the dimensionality.”