Control Theory and Experimental Design in Diffusion Processes

DOI10.1137/140962280zbMATH Open1327.62437arXiv1210.3739OpenAlexW2079754921MaRDI QIDQ2945147FDOQ2945147

Authors: Giles Hooker, Kevin K. Lin, Bruce Rogers 

Publication date: 9 September 2015

Published in: SIAM/ASA Journal on Uncertainty Quantification (Search for Journal in Brave)

Abstract: This paper considers the problem of designing time-dependent, real-time control policies for controllable nonlinear diffusion processes, with the goal of obtaining maximally-informative observations about parameters of interest. More precisely, we maximize the expected Fisher information for the parameter obtained over the duration of the experiment, conditional on observations made up to that time. We propose to accomplish this with a two-step strategy: when the full state vector of the diffusion process is observable continuously, we formulate this as an optimal control problem and apply numerical techniques from stochastic optimal control to solve it. When observations are incomplete, infrequent, or noisy, we propose using standard filtering techniques to first estimate the state of the system, then apply the optimal control policy using the posterior expectation of the state. We assess the effectiveness of these methods in 3 situations: a paradigmatic bistable model from statistical physics, a model of action potential generation in neurons, and a model of a simple ecological system.

Full work available at URL: https://arxiv.org/abs/1210.3739

Recommendations

• scientific article; zbMATH DE number 4006128
• Ergodic control of diffusion processes
• scientific article; zbMATH DE number 42423
• Control of diffusion processes in \(\mathbb R^N\)
• Ergodic control of diffusion processes.
• scientific article; zbMATH DE number 4038607
• Controlled diffusion processes
• scientific article; zbMATH DE number 3932148
• scientific article; zbMATH DE number 1071411
• Controllability in dynamics of diffusion processes with nonlocal conditions

zbMATH Keywords

design of experimentsstochastic optimal controlstochastic population dynamicscontrolled diffusionsneuron dynamics

Mathematics Subject Classification ID

Optimal statistical designs (62K05) Sequential statistical design (62L05) Population dynamics (general) (92D25) Neural biology (92C20) Dynamic programming in optimal control and differential games (49L20) Discrete approximations in optimal control (49M25) Optimal stochastic control (93E20)

Cites Work

• Monte Carlo strategies in scientific computing.
• Dynamic relations for sparsely sampled Gaussian processes
• Bayesian experimental design: A review
• Title not available (Why is that?)
• A random map implementation of implicit filters
• Parameter Estimation for Differential Equations: a Generalized Smoothing Approach
• Stochastic simulation: Algorithms and analysis
• Title not available (Why is that?)
• Optimal Bayesian design applied to logistic regression experiments
• Parameter estimation of ODE's via nonparametric estimators
• Riemann manifold Langevin and Hamiltonian Monte Carlo methods. With discussion and authors' reply
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Stochastic modelling for systems biology.
• Mathematical foundations of neuroscience
• Closed-form likelihood expansions for multivariate diffusions
• Stochastic processes in physics and chemistry.
• Random Perturbations of Dynamical Systems
• Title not available (Why is that?)
• Title not available (Why is that?)
• Limit theorems for sequences of jump Markov processes approximating ordinary differential processes
• Approximate Dynamic Programming
• Title not available (Why is that?)
• Nonlinear Experiments: Optimal Design and Inference Based on Likelihood
• Fast numerical methods for stochastic computations: a review
• Numerical methods for optimum experimental design in DAE systems
• Approximate dynamic programming and its applications to the design of Phase I cancer trials
• Forcing Function Diagnostics for Nonlinear Dynamics
• Experimental design for partially observed Markov decision processes
• A separation theorem for nonlinear systems
• Optimal experimental design for sampling voltage on dendritic trees in the low-SNR regime
• Bayesian experimental design for long-term longitudinal HIV dynamic studies

Cited In (9)

• Title not available (Why is that?)
• Adaptive treatment and robust control
• Optimal design for estimation in diffusion processes from first hitting times
• Title not available (Why is that?)
• Goodness of fit in nonlinear dynamics: misspecified rates or misspecified states?
• A new actuator activation policy for performance enhancement of controlled diffusion processes.
• Transient dynamics of Pearson diffusions facilitates estimation of rate parameters
• Experimental design for partially observed Markov decision processes
• Timing observations of diffusions

Uses Software

• VPLAN
• StochSens

This page was built for publication: Control Theory and Experimental Design in Diffusion Processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2945147)