Target Shapley effects for high-dimensional correlated reliability problems can be estimated from a single failing sample by rewriting closed target Sobol indices via conditional densities and fitting those densities with normalizing flows.
Rare event probability learning by normalizing flows
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
A sequential Monte Carlo simulation approach with fixed-level splitting efficiently estimates rare non-recovery probabilities in resilient wireless networks and extends to generative models for digital twins.
citing papers explorer
-
High-dimensional reliability-oriented Shapley effect estimation with Normalizing Flows
Target Shapley effects for high-dimensional correlated reliability problems can be estimated from a single failing sample by rewriting closed target Sobol indices via conditional densities and fitting those densities with normalizing flows.
-
Sequential Monte Carlo for Resilient Networks: Assessment, Mitigation, and Generative Modeling
A sequential Monte Carlo simulation approach with fixed-level splitting efficiently estimates rare non-recovery probabilities in resilient wireless networks and extends to generative models for digital twins.