Further results on probabilistic model validation in Wasserstein metric

In a recent work [1], we have introduced a probabilistic formulation for the model validation problem to provide a unifying framework for (in)validating nonlinear deterministic and stochastic models, in both discrete and continuous time. As an extension to that work, this paper provides rigorous performance bounds for the model validation algorithms presented in [1]. Further, it is shown that the existing method of barrier certificate based nonlinear invalidation oracle, can be recovered as a special case of the proposed formulation. Some results are derived to quantify the effects of initial uncertainty on the Wasserstein gap. And finally, for discrete-time LTI and LTV systems, upper bounds on Wasserstein distance are derived in terms of the parameters of the systems under comparison, thus providing an offline estimate of the gap.

[1]  C. Givens,et al.  A class of Wasserstein metrics for probability distributions. , 1984 .

[2]  R. Bhattacharya,et al.  Hypersonic State Estimation Using the Frobenius-Perron Operator , 2011 .

[3]  S. Rachev.  The Monge–Kantorovich Mass Transference Problem and Its Stochastic Applications , 1985 .

[4]  Pramod Khargonekar,et al.  A Time-Domain Approach to Model Validation , 1992, 1992 American Control Conference.

[5]  Patrick Cattiaux,et al.  A CRITERION FOR TALAGRAND'S QUADRATIC TRANSPORTATION COST INEQUALITY. , 2008 .

[6]  Pablo A. Parrilo,et al.  Introducing SOSTOOLS: a general purpose sum of squares programming solver , 2002, Proceedings of the 41st IEEE Conference on Decision and Control, 2002..

[7]  D. Kinderlehrer,et al.  THE VARIATIONAL FORMULATION OF THE FOKKER-PLANCK EQUATION , 1996 .

[8]  G. Burton.  TOPICS IN OPTIMAL TRANSPORTATION (Graduate Studies in Mathematics 58) By CÉDRIC VILLANI: 370 pp., US$59.00, ISBN 0-8218-3312-X (American Mathematical Society, Providence, RI, 2003) , 2004 .

[9]  W. Gilchrist,et al.  Statistical Modelling with Quantile Functions , 2000 .

[10]  S. S. Vallender.  Calculation of the Wasserstein Distance Between Probability Distributions on the Line , 1974 .

[11]  Thibaut Le Gouic,et al.  "Exact" deviations in Wasserstein distance for empirical and occupation measures , 2011 .

[12]  William T. Shaw,et al.  Quantile mechanics , 2008, European Journal of Applied Mathematics.

[13]  Abhishek Halder,et al.  Model validation: A probabilistic formulation , 2011, IEEE Conference on Decision and Control and European Control Conference.

[14]  S. Prajna.  Barrier certificates for nonlinear model validation , 2003, 42nd IEEE International Conference on Decision and Control (IEEE Cat. No.03CH37475).

[15]  Abhishek Halder,et al.  Dispersion Analysis in Hypersonic Flight During Planetary Entry Using Stochastic Liouville Equation , 2011 .

[16]  Guoxiang Gu,et al.  LFT uncertain model validation with time- and frequency-domain measurements , 1999, IEEE Trans. Autom. Control..

[17]  C. Villani.  Topics in Optimal Transportation , 2003 .

[18]  A. Guillin,et al.  Transportation cost-information inequalities and applications to random dynamical systems and diffusions , 2004, math/0410172.

[19]  Alexander J. McNeil.  Statistical Modeling With Quantile Functions , 2001 .

[20]  Abhishek Halder,et al.  Beyond Monte Carlo: A Computational Framework for Uncertainty Propagation in Planetary Entry, Descent and Landing , 2010 .

[21]  Suman Chakravorty,et al.  A semianalytic meshless approach to the transient Fokker–Planck equation , 2010 .

[22]  Kenji Fukumizu,et al.  On integral probability metrics, φ-divergences and binary classification , 2009, 0901.2698.

[23]  Rajeev Motwani,et al.  Randomized algorithms , 1996, CSUR.

[24]  John Doyle,et al.  Model validation: a connection between robust control and identification , 1992 .

[25]  Jim Freeman.  Probability Metrics and the Stability of Stochastic Models , 1991 .