Scalable Information Inequalities for Uncertainty Quantification

Abstract

In this paper we demonstrate the only available scalable information bounds for quantities of interest of high dimensional probabilistic models. Scalability of inequalities allows us to (a) obtain uncertainty quantification bounds for quantities of interest in the large degree of freedom limit and/or at long time regimes; (b) assess the impact of large model perturbations as in nonlinear response regimes in statistical mechanics; (c) address model-form uncertainty, i.e. compare different extended models and corresponding quantities of interest. We demonstrate some of these properties by deriving robust uncertainty quantification bounds for phase diagrams in statistical mechanics models.

References in corpus (2)

• Frenetic aspects of second order response
• A Relative Entropy Rate Method for Path Space Sensitivity Analysis of Stationary Complex Stochastic Dynamics

Cited by in corpus (9)

• Irreversibility, Loschmidt echo, and thermodynamic uncertainty relation
• Uncertainty Quantification for Markov Processes via Variational Principles and Functional Inequalities
• A Tight Lower Bound for the Hellinger Distance with Given Means and Variances
• Robust information divergences for model-form uncertainty arising from sparse data in random PDE
• Novel Change of Measure Inequalities with Applications to PAC-Bayesian Bounds and Monte Carlo Estimation
• Concentration Inequalities and UQ Bounds for Hypocoercive MCMC Samplers
• Distributional Robustness and Uncertainty Quantification for Rare Events
• Quantification of Model Uncertainty on Path-Space via Goal-Oriented Relative Entropy
• Tight Lower Bounds for $\alpha$-Divergences Under Moment Constraints and Relations Between Different $\alpha$