Accelerating inference for stochastic kinetic models
From MaRDI portal
Abstract: Stochastic kinetic models (SKMs) are increasingly used to account for the inherent stochasticity exhibited by interacting populations of species in areas such as epidemiology, population ecology and systems biology. Species numbers are modelled using a continuous-time stochastic process, and, depending on the application area of interest, this will typically take the form of a Markov jump process or an It^o diffusion process. Widespread use of these models is typically precluded by their computational complexity. In particular, performing exact fully Bayesian inference in either modelling framework is challenging due to the intractability of the observed data likelihood, necessitating the use of computationally intensive techniques such as particle Markov chain Monte Carlo (particle MCMC). It is proposed to increase the computational and statistical efficiency of this approach by leveraging the tractability of an inexpensive surrogate derived directly from either the jump or diffusion process. The surrogate is used in three ways: in the design of a gradient-based parameter proposal, to construct an appropriate bridge and in the first stage of a delayed-acceptance step. The resulting approach, which exactly targets the posterior of interest, offers substantial gains in efficiency over a standard particle MCMC implementation.
Recommendations
- Bayesian computation methods for inference in stochastic kinetic models
- Bayesian Inference for Stochastic Kinetic Models Using a Diffusion Approximation
- Bayesian inference for hybrid discrete-continuous stochastic kinetic models
- Delayed acceptance particle MCMC for exact inference in stochastic kinetic models
- Moment closure based parameter inference of stochastic kinetic models
- Towards Confident Bayesian Parameter Estimation in Stochastic Chemical Kinetics
- Approximation and inference methods for stochastic biochemical kinetics -- a tutorial review
- Fast and precise inference on diffusivity in interacting particle systems
- Efficient stochastic model for the point kinetics equations
- Solving stochastic chemical kinetics by metropolis-Hastings sampling
Cites work
- A lognormal central limit theorem for particle approximations of normalizing constants
- A population Monte Carlo scheme with transformed weights and its application to stochastic kinetic models
- Asymptotically exact inference in differentiable generative models
- Bayesian inference for diffusion-driven mixed-effects models
- Bayesian inference for irreducible diffusion processes using the pseudo-marginal approach
- Bayesian inference for Markov jump processes with informative observations
- Birth/birth-death processes and their computable transition probabilities with biological applications
- Correlated pseudo-marginal schemes for time-discretised stochastic kinetic models
- Delayed acceptance particle MCMC for exact inference in stochastic kinetic models
- Efficiency of delayed-acceptance random walk metropolis algorithms
- Efficient implementation of Markov chain Monte Carlo when using an unbiased likelihood estimator
- Efficient sampling of conditioned Markov jump processes
- Exponential convergence of Langevin distributions and their discrete approximations
- scientific article; zbMATH DE number 5717665 (Why is no real title available?)
- scientific article; zbMATH DE number 3786561 (Why is no real title available?)
- scientific article; zbMATH DE number 2106098 (Why is no real title available?)
- Improved bridge constructs for stochastic differential equations
- Inference for Diffusion Processes
- Inference for reaction networks using the linear noise approximation
- Langevin diffusions and Metropolis-Hastings algorithms
- Large-sample asymptotics of the pseudo-marginal method
- Likelihood free inference for Markov processes: a comparison
- Majorize–Minimize Adapted Metropolis–Hastings Algorithm
- Markov chain Monte Carlo inference for Markov jump processes via the linear noise approximation
- Modeling infectious diseases in humans and animals
- On some properties of Markov chain Monte Carlo simulation methods based on the particle filter
- On the efficiency of pseudo-marginal random walk Metropolis algorithms
- Optimal Scaling of Discrete Approximations to Langevin Diffusions
- Particle approximations of the score and observed information matrix in state space models with application to parameter estimation
- Particle Markov chain Monte Carlo for efficient numerical simulation
- Particle Metropolis-adjusted Langevin algorithms
- Scalable inference for Markov processes with intractable likelihoods
- Sequential Bayesian inference in hidden Markov stochastic kinetic models with application to detection and response to seasonal epidemics
- Simulation-based Bayesian inference for epidemic models
- Speeding up MCMC by Delayed Acceptance and Data Subsampling
- Stochastic approach to chemical kinetics
- Stochastic processes in physics and chemistry.
- The alive particle filter and its use in particle Markov chain Monte Carlo
- The correlated pseudomarginal method
- Unbiased Bayesian inference for population Markov jump processes via random truncations
Cited in
(4)- Preconditioned Bayesian regression for stochastic chemical kinetics
- A survey of Monte Carlo methods for noisy and costly densities with application to reinforcement learning and ABC
- Particle Gibbs for likelihood-free inference of stochastic volatility models
- Nested ensemble Kalman filter for static parameter inference in nonlinear state-space models
This page was built for publication: Accelerating inference for stochastic kinetic models
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6115546)
