Convex Parameter Recovery for Interacting Marked Processes

We introduce a new general modeling approach for multivariate discrete event data with categorical interacting marks, which we refer to as marked Bernoulli processes. In the proposed model, the probability of an event of a specific category to occur in a location may be influenced by past events at this and other locations. We do not restrict interactions to be positive or decaying over time as it is commonly adopted, allowing us to capture an arbitrary shape of influence from historical events, locations, and events of different categories. In our modeling, prior knowledge is incorporated by allowing general convex constraints on model parameters. We develop two parameter estimation procedures utilizing the constrained Least Squares (LS) and Maximum Likelihood (ML) estimation, which are solved using variational inequalities with monotone operators. We discuss different applications of our approach and illustrate the performance of proposed recovery routines on synthetic examples and a real-world police dataset.

[1]  Kazuoki Azuma WEIGHTED SUMS OF CERTAIN DEPENDENT RANDOM VARIABLES , 1967 .

[2]  A. Hawkes Point Spectra of Some Mutually Exciting Point Processes , 1971 .

[3]  A. Hawkes Spectra of some self-exciting and mutually exciting point processes , 1971 .

[4]  A. Hawkes,et al.  A cluster process representation of a self-exciting process , 1974, Journal of Applied Probability.

[5]  D. Freedman On Tail Probabilities for Martingales , 1975 .

[6]  Y. Nesterov Semidefinite relaxation and nonconvex quadratic optimization , 1998 .

[7]  Vladimir Spokoiny,et al.  Deviation probability bound for martingales with applications to statistical estimation , 2000 .

[8]  M. Kuperman,et al.  Small world effect in an epidemiological model. , 2000, Physical review letters.

[9]  J. Møller,et al.  Statistical Inference and Simulation for Spatial Point Processes , 2003 .

[10]  Andrea L. Bertozzi,et al.  c ○ World Scientific Publishing Company A STATISTICAL MODEL OF CRIMINAL BEHAVIOR , 2008 .

[11]  George E. Tita,et al.  Self-Exciting Point Process Modeling of Crime , 2011 .

[12]  P. Embrechts,et al.  Multivariate Hawkes processes: an application to financial data , 2011, Journal of Applied Probability.

[13]  Xiequan Fan,et al.  Hoeffding’s inequality for supermartingales , 2011, 1109.4359.

[14]  A. Stomakhin,et al.  Reconstruction of missing data in social networks based on temporal patterns of interactions , 2011 .

[15]  George Mohler,et al.  Modeling and estimation of multi-source clustering in crime and security data , 2013, 1311.7279.

[16]  Le Song,et al.  Learning Social Infectivity in Sparse Low-rank Networks Using Multi-dimensional Hawkes Processes , 2013, AISTATS.

[17]  Bernhard Schölkopf,et al.  Modeling Information Propagation with Survival Theory , 2013, ICML.

[18]  B. Delyon,et al.  Concentration Inequalities for Sums and Martingales , 2015 .

[19]  C. Rudin,et al.  Reactive point processes: A new approach to predicting power failures in underground electrical systems , 2015, 1505.07661.

[20]  Lasso and probabilistic inequalities for multivariate point processes , 2015, 1208.0570.

[21]  Eric Warren Fox,et al.  Spatially inhomogeneous background rate estimators and uncertainty quantification for nonparametric Hawkes point process models of earthquake occurrences , 2016 .

[22]  Peter Szolovits,et al.  MIMIC-III, a freely accessible critical care database , 2016, Scientific Data.

[23]  Andrea L. Bertozzi,et al.  Topic Time Series Analysis of Microblogs , 2016 .

[24]  Rebecca Willett,et al.  Tracking Dynamic Point Processes on Networks , 2014, IEEE Transactions on Information Theory.

[25]  Marta Blangiardo,et al.  A Bayesian Approach to Modelling Fine-Scale Spatial Dynamics of Non-State Terrorism: World Study, 2002-2013 , 2016, 1610.01215.

[26]  R. Dahlhaus,et al.  Graphical Modeling for Multivariate Hawkes Processes with Nonparametric Link Functions , 2016, 1605.06759.

[27]  Eric T. Shea-Brown,et al.  The Multivariate Hawkes Process in High Dimensions: Beyond Mutual Excitation , 2017, 1707.04928.

[28]  Shuang Li,et al.  Detecting Changes in Dynamic Events Over Networks , 2017, IEEE Transactions on Signal and Information Processing over Networks.

[29]  Hongyuan Zha,et al.  THAP: A Matlab Toolkit for Learning with Hawkes Processes , 2017, ArXiv.

[30]  E. Fox,et al.  Granger Causality Networks for Categorical Time Series , 2017, 1706.02781.

[31]  Alex Reinhart,et al.  A Review of Self-Exciting Spatio-Temporal Point Processes and Their Applications , 2017, Statistical Science.

[32]  Gordon J. Ross,et al.  Bayesian hierarchical modelling of sparse count processes in retail analytics , 2018, 1805.05657.

[33]  Anatoli B. Juditsky,et al.  Signal Recovery by Stochastic Optimization , 2019, Automation and Remote Control.

[34]  Mason A. Porter,et al.  Multivariate Spatiotemporal Hawkes Processes and Network Reconstruction , 2018, SIAM J. Math. Data Sci..