Online Discovery for Stable and Grouping Causalities in Multivariate Time Series
The content of this chapter is organized as follows: The problem formulation is presented in Sect. 10.1. Section 10.2 introduces the details about our proposed approach and its equivalent Bayesian model. A solution capable of online inference with particle learning is given in Sect. 10.3. Extensive empirical evaluation is demonstrated in Sect. 10.4. Finally, we conclude our work and discuss the future work.
KeywordsGranger causality Elastic-net regularizer Hadamard product VAR-elastic-net Random walk Piecewise constant Lasso regularization
- [LLNM+09]A.C. Lozano, H. Li, A. Niculescu-Mizil, Y. Liu, C. Perlich, J. Hosking, N. Abe, Spatial-temporal causal modeling for climate change attribution, in Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining (ACM, New York, 2009), pp. 587–596Google Scholar