Genealogical particle analysis of rare events

Abstract

In this paper an original interacting particle system approach is developed for studying Markov chains in rare event regimes. The proposed particle system is theoretically studied through a genealogical tree interpretation of Feynman--Kac path measures. The algorithmic implementation of the particle system is presented. An estimator for the probability of occurrence of a rare event is proposed and its variance is computed, which allows to compare and to optimize different versions of the algorithm. Applications and numerical implementations are discussed. First, we apply the particle system technique to a toy model (a Gaussian random walk), which permits to illustrate the theoretical predictions. Second, we address a physically relevant problem consisting in the estimation of the outage probability due to polarization-mode dispersion in optical fibers.

Published at http://dx.doi.org/10.1214/105051605000000566 in the Annals of Applied Probability (http://www.imstat.org/aap/) by the Institute of Mathematical Statistics (http://www.imstat.org)

References in corpus (1)

• A Berry-Esseen theorem for Feynman-Kac and interacting particle models

Cited by in corpus (44)

• Population dynamics method with a multi-canonical feedback control
• The instanton method and its numerical implementation in fluid mechanics
• Rare event algorithm study of extreme warm summers and heat waves over Europe
• Exact fluctuations of nonequilibrium steady states from approximate auxiliary dynamics
• Particle filters
• Practical rare event sampling for extreme mesoscale weather
• Computing return times or return periods with rare event algorithms
• Rare event computation in deterministic chaotic systems using genealogical particle analysis
• Applications of large deviation theory in geophysical fluid dynamics and climate science
• Finite-time and finite-size scalings in the evaluation of large-deviation functions: Analytical study using a birth-death process
• Optimizing weighted ensemble sampling of steady states
• Analysis and optimization of weighted ensemble sampling
• Application of Adaptive Multilevel Splitting to High-Dimensional Dynamical Systems
• Rare Event Sampling Improves Mercury Instability Statistics
• Computation of extremes values of time averaged observables in climate models with large deviation techniques
• Small noise asymptotic of the timing jitter in soliton transmission
• A sequential Monte Carlo approach to computing tail probabilities in stochastic models
• Asymptotic genealogies of interacting particle systems with an application to sequential Monte Carlo
• Constructing Auxiliary Dynamics for Nonequilibrium Stationary States by Variance Minimization
• On a new class of score functions to estimate tail probabilities of some stochastic processes with Adaptive Multilevel Splitting
• On particle Gibbs Markov chain Monte Carlo models
• Large deviations for weighted empirical measures arising in importance sampling
• Min-max representations of viscosity solutions of Hamilton-Jacobi equations and applications in rare-event simulation
• An ergodic theorem for the weighted ensemble method
• Simulation of diffusions by means of importance sampling paradigm
• Optimal input potential functions in the interacting particle system method
• A self-similarity principle for the computation of rare event probability
• Using rare event algorithms to understand the statistics and dynamics of extreme heatwave seasons in South Asia
• On the concentration properties of Interacting particle processes
• Inference and rare event simulation for stopped Markov processes via reverse-time sequential Monte Carlo
• Unbiased simulation of rare events in continuous time
• Rare Event Simulation for Steady-State Probabilities via Recurrency Cycles
• Sequential Monte Carlo with Highly Informative Observations
• Application of the interacting particle system method to piecewise deterministic Markov processes used in reliability
• Adversarial sampling of unknown and high-dimensional conditional distributions
• A splitting method to reduce MCMC variance
• Towards Data-Conditional Simulation for ABC Inference in Stochastic Differential Equations
• Bounding rare event probabilities in computer experiments
• Density-dependent stochastic resetting: a large deviations framework for achieving target distributions over networks
• Splitting for Rare Event Simulation: A Large Deviation Approach to Design and Analysis
• Generalizing Parallel Replica Dynamics: Trajectory Fragments, Asynchronous Computing, and PDMPs
• Some Contributions to Sequential Monte Carlo Methods for Option Pricing
• Monte-Carlo acceleration: importance sampling and hybrid dynamic systems
• Bayesian Parameter Inference for Partially Observed Stopped Processes