LICORS: Light Cone Reconstruction of States for Non-parametric Forecasting of Spatio-Temporal Systems

We present a new, non-parametric forecasting method for data where continuous values are observed discretely in space and time. Our method, "light-cone reconstruction of states" (LICORS), uses physical principles to identify predictive states which are local properties of the system, both in space and time. LICORS discovers the number of predictive states and their predictive distributions automatically, and consistently, under mild assumptions on the data source. We provide an algorithm to implement our method, along with a cross-validation scheme to pick control settings. Simulations show that CV-tuned LICORS outperforms standard methods in forecasting challenging spatio-temporal dynamics. Our work provides applied researchers with a new, highly automatic method to analyze and forecast spatio-temporal data.

[1]  Denis Bosq,et al.  Nonparametric statistics for stochastic processes , 1996 .

[2]  R. Brotman,et al.  A functional approach. , 1970, International journal of psychiatry.

[3]  J. A. Stewart,et al.  Nonlinear Time Series Analysis , 2015 .

[4]  Helmut Ltkepohl,et al.  New Introduction to Multiple Time Series Analysis , 2007 .

[5]  Ulrike von Luxburg,et al.  A tutorial on spectral clustering , 2007, Stat. Comput..

[6]  Martin J. Wainwright,et al.  A More Powerful Two-Sample Test in High Dimensions using Random Projection , 2011, NIPS.

[7]  John Odenckantz,et al.  Nonparametric Statistics for Stochastic Processes: Estimation and Prediction , 2000, Technometrics.

[8]  Noel A Cressie,et al.  Statistics for Spatio-Temporal Data , 2011 .

[9]  Evgueni A. Haroutunian,et al.  Information Theory and Statistics , 2011, International Encyclopedia of Statistical Science.

[10]  John Langford,et al.  Learning nonlinear dynamic models , 2009, ICML '09.

[11]  Jeffery R. Westbrook,et al.  A Functional Approach to External Graph Algorithms , 1998, Algorithmica.

[12]  Heike Leitte.  Information theoretic methods for the visual analysis of climate and flow data , 2009 .

[13]  James P. Crutchfield,et al.  Computational Mechanics: Pattern and Prediction, Structure and Simplicity , 1999, ArXiv.

[14]  Frank B. Knight,et al.  Foundations of the Prediction Process , 1992 .

[15]  Christian P. Robert,et al.  Statistics for Spatio-Temporal Data , 2014 .

[16]  Sergei Vassilvitskii,et al.  k-means++: the advantages of careful seeding , 2007, SODA '07.

[17]  Roberto Fernández,et al.  Chains with Complete Connections: General Theory, Uniqueness, Loss of Memory and Mixing Properties , 2003, math/0305026.

[18]  Bernhard Schölkopf,et al.  A Kernel Method for the Two-Sample-Problem , 2006, NIPS.

[19]  Jiti Gao,et al.  Nonlinear Time Series: Semiparametric and Nonparametric Methods , 2019 .

[20]  Parlitz,et al.  Prediction of spatiotemporal time series based on reconstructed local states , 2000, Physical review letters.

[21]  Robert Haslinger,et al.  Quantifying self-organization with optimal predictors. , 2004, Physical review letters.

[22]  P. Bickel,et al.  Large Vector Auto Regressions , 2011, 1106.3915.

[23]  Denis Bosq,et al.  Inference and prediction in large dimensions , 2007 .

[24]  M. Dolores Ugarte,et al.  Statistical Methods for Spatio-temporal Systems , 2006 .

[25]  Young,et al.  Inferring statistical complexity. , 1989, Physical review letters.

[26]  L. Wasserman.  All of Nonparametric Statistics , 2005 .

[27]  Richard S. Sutton,et al.  Predictive Representations of State , 2001, NIPS.

[28]  Herbert Jaeger,et al.  Observable Operator Models for Discrete Stochastic Time Series , 2000, Neural Computation.

[29]  V. Capasso,et al.  Stochastic Geometry of Spatially Structured Birth and Growth Processes. Application to Crystallization Processes , 2003 .

[30]  P. Rosenbaum.  An exact distribution‐free test comparing two multivariate distributions based on adjacency , 2005 .

[31]  W. Salmon,et al.  Commentary Scientific Explanation and the Causal Structure of the World , 2012 .

[32]  J. Woodward,et al.  Scientific Explanation and the Causal Structure of the World , 1988 .

[33]  P. Grassberger.  Toward a quantitative theory of self-generated complexity , 1986 .

[34]  Cosma Rohilla Shalizi.  Optimal Nonlinear Prediction of Random Fields on Networks , 2003, DMCS.

[35]  Maria L. Rizzo,et al.  DISCO analysis: A nonparametric extension of analysis of variance , 2010, 1011.2288.

[36]  N. Wermuth,et al.  Nonlinear Time Series: Nonparametric and Parametric Methods , 2005 .

[37]  R. Varga,et al.  Proof of Theorem 4 , 1983 .

[38]  S. Caires,et al.  On the Non-parametric Prediction of Conditionally Stationary Sequences , 2005 .

[39]  W. Hoeffding.  Probability Inequalities for sums of Bounded Random Variables , 1963 .

[40]  Frank B. Knight,et al.  A Predictive View of Continuous Time Processes , 1975 .

[41]  Gerik Scheuermann,et al.  Multifield visualization using local statistical complexity , 2007, IEEE Transactions on Visualization and Computer Graphics.

[42]  Wesley C. Salmon,et al.  Statistical explanation & statistical relevance , 1971 .

[43]  Larry Wasserman,et al.  Spectral Connectivity Analysis , 2008, 0811.0121.