Uncertainty quantification for Markov processes via variational principles and functional inequalities
From MaRDI portal
Abstract: Information-theory based variational principles have proven effective at providing scalable uncertainty quantification (i.e. robustness) bounds for quantities of interest in the presence of nonparametric model-form uncertainty. In this work, we combine such variational formulas with functional inequalities (Poincar{'e}, -Sobolev, Liapunov functions) to derive explicit uncertainty quantification bounds for time-averaged observables, comparing a Markov process to a second (not necessarily Markov) process. These bounds are well-behaved in the infinite-time limit and apply to steady-states of both discrete and continuous-time Markov processes.
Recommendations
- Variational principles for asymptotic variance of general Markov processes
- Scalable information inequalities for uncertainty quantification
- A variational principle for Markov processes
- deviation bounds for additive functionals of markov processes
- Chernoff and Berry–Esséen inequalities for Markov processes
Cites work
- A deviation inequality for non-reversible Markov processes
- A short course on operator semigroups
- A simple proof of the Poincaré inequality for a large class of probability measures
- Applied Semi-Markov Processes
- Bernstein-type concentration inequalities for symmetric Markov processes
- Binomial-Poisson entropic inequalities and the M/M/∞queue
- Chernoff and Berry–Esséen inequalities for Markov processes
- Comparison theorems for reversible Markov chains
- Concentration inequalities. A nonasymptotic theory of independence
- Continuous time Markov processes. An introduction.
- deviation bounds for additive functionals of markov processes
- Distinguishing and integrating aleatoric and epistemic variation in uncertainty quantification
- Examples of fitting structured phase–type distributions
- How Biased Is Your Model? Concentration Inequalities, Information and Model Bias
- scientific article; zbMATH DE number 3897964 (Why is no real title available?)
- scientific article; zbMATH DE number 192908 (Why is no real title available?)
- scientific article; zbMATH DE number 1236226 (Why is no real title available?)
- scientific article; zbMATH DE number 1153603 (Why is no real title available?)
- scientific article; zbMATH DE number 3344968 (Why is no real title available?)
- scientific article; zbMATH DE number 2237386 (Why is no real title available?)
- Hypocoercivity for kinetic equations with linear relaxation terms
- Hypocoercivity for linear kinetic equations conserving mass
- Information metrics for long-time errors in splitting schemes for stochastic dynamics and parallel kinetic Monte Carlo
- Large deviations techniques and applications.
- Logarithmic Sobolev inequalities and spectral gaps
- Logarithmic Sobolev inequalities for finite Markov chains
- Lower bounds for eigenvalues of regular Sturm-Liouville operators and the logarithmic Sobolev inequality
- Markov chains and mixing times. With a chapter on ``Coupling from the past by James G. Propp and David B. Wilson.
- Matrix-Exponential Distributions in Applied Probability
- Measuring distribution model risk
- Noisy Monte Carlo: convergence of Markov chains with approximate transition kernels
- On Divergences and Informations in Statistics and Information Theory
- On the entropy for semi-Markov processes
- Path-space information bounds for uncertainty quantification and sensitivity analysis of stochastic dynamics
- Perturbation theory for Markov chains via Wasserstein distance
- Poincaré inequality and the \(L^{p}\) convergence of semi-groups
- Randomized Hamiltonian Monte Carlo as scaling limit of the bouncy particle sampler and dimension-free convergence rates
- Rate of convergence for ergodic continuous Markov processes: Lyapunov versus Poincaré
- Regular Perturbation of V-Geometrically Ergodic Markov Chains
- Robust risk measurement and model risk
- Robust sensitivity analysis for stochastic systems
- Scalable information inequalities for uncertainty quantification
- Semi-Markov processes and reliability
- Sensitivity and convergence of uniformly ergodic Markov chains
- Stability of noisy Metropolis-Hastings
- Transportation-information inequalities for Markov processes
- Yet Another Look at Harris’ Ergodic Theorem for Markov Chains
Cited in
(8)- Scalable information inequalities for uncertainty quantification
- Large deviations of empirical measures of diffusions in weighted topologies
- Quantification of model uncertainty on path-space via goal-oriented relative entropy
- Model Uncertainty and Correctability for Directed Graphical Models
- Uncertainty quantification for Markov random fields
- Overcoming the timescale barrier in molecular dynamics: Transfer operators, variational principles and machine learning
- Quantifying and Managing Uncertainty in Piecewise-Deterministic Markov Processes
- Concentration inequalities and UQ bounds for hypocoercive MCMC samplers
This page was built for publication: Uncertainty quantification for Markov processes via variational principles and functional inequalities
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4961000)
