Data free inference with processed data products

We consider the context of probabilistic inference of model parameters given error bars or confidence intervals on model output values, when the data is unavailable. We introduce a class of algorithms in a Bayesian framework, relying on maximum entropy arguments and approximate Bayesian computation methods, to generate consistent data with the given summary statistics. Once we obtain consistent data sets, we pool the respective posteriors, to arrive at a single, averaged density on the parameters. This approach allows us to perform accurate forward uncertainty propagation consistent with the reported statistics.

[1]  Phil Gregory.  Bayesian Logical Data Analysis for the Physical Sciences: References , 2005 .

[2]  Dongbin Xiu,et al.  The Wiener-Askey Polynomial Chaos for Stochastic Differential Equations , 2002, SIAM J. Sci. Comput..

[3]  Xiangyu Wang,et al.  Parallel MCMC via Weierstrass Sampler , 2013, ArXiv.

[4]  Cosmin Safta,et al.  Uncertainty quantification of reaction mechanisms accounting for correlations introduced by rate rules and fitted Arrhenius parameters , 2013 .

[5]  D. Xiu.  Fast numerical methods for stochastic computations: A review , 2009 .

[6]  U. von Toussaint,et al.  Bayesian inference and maximum entropy methods in science and engineering , 2004 .

[7]  J. Lynch,et al.  A weak convergence approach to the theory of large deviations , 1997 .

[8]  Charles Raymond Smith,et al.  BAYESIAN INFERENCE AND MAXIMUM ENTROPY METHODS IN SCIENCE AND ENGINEERING , 2001 .

[9]  Chong Wang,et al.  Asymptotically Exact, Embarrassingly Parallel MCMC , 2013, UAI.

[10]  M. Schervish,et al.  Characterization of Externally Bayesian Pooling Operators , 1986 .

[11]  Simon R. White,et al.  Fast Approximate Bayesian Computation for discretely observed Markov models using a factorised posterior distribution , 2013, 1301.2975.

[12]  E. Jaynes.  Information Theory and Statistical Mechanics , 1957 .

[13]  Thomas M. Cover,et al.  Elements of Information Theory , 2005 .

[14]  Theodore Kypraios,et al.  Piecewise Approximate Bayesian Computation: fast inference for discretely observed Markov models using a factorised posterior distribution , 2015, Stat. Comput..

[15]  D. Balding,et al.  Approximate Bayesian computation in population genetics. , 2002, Genetics.

[16]  Habib N. Najm,et al.  Data-free inference of the joint distribution of uncertain model parameters , 2010, J. Comput. Phys..

[17]  S. Sisson,et al.  Likelihood-free Markov chain Monte Carlo , 2010, 1001.2058.

[18]  Ariel Caticha,et al.  Entropic Inference , 2010, 1011.0723.

[19]  P. Pernot,et al.  How measurements of rate coefficients at low temperature increase the predictivity of photochemical models of Titan's atmosphere. , 2009, The journal of physical chemistry. A.

[20]  Stephen P. Boyd,et al.  Convex Optimization , 2004, Algorithms and Theory of Computation Handbook.