A system identification approach to clustering vector autoregressive time series

Clustering of time series based on their underlying dynamics is keeping attracting researchers due to its impacts on assisting complex system modelling. Most current time series clustering methods handle only scalar time series, treat them as white noise, or rely on domain knowledge for high-quality feature construction, where the autocorrelation pattern/feature is mostly ignored. Instead of relying on heuristic feature/metric construction, the system identification approach allows treating vector time series clustering by explicitly considering their underlying autoregressive dynamics. We first derive a clustering algorithm based on a mixture autoregressive model. Unfortunately it turns out to have significant computational problems. We then derive a `small-noise' limiting version of the algorithm, which we call k-LMVAR (Limiting Mixture Vector AutoRegression), that is computationally manageable. We develop an associated BIC criterion for choosing the number of clusters and model order. The algorithm performs very well in comparative simulations and also scales well computationally.

k-MLE, k-Bregman, k-VARs: Theory, Convergence, Computation

We develop hard clustering based on likelihood rather than distance and prove convergence. We also provide simulations and real data examples.

Asymptotic Classification Error for Heavy-Tailed Renewal Processes

Despite the widespread occurrence of classification problems and the increasing collection of point process data across many disciplines, study of error probability for point process classification only emerged very recently. Here, we consider classification of renewal processes. We obtain asymptotic expressions for the Bhattacharyya bound on misclassification error probabilities for heavy-tailed renewal processes.

Asymptotic Error Rates for Point Process Classification

Point processes are finding growing applications in numerous fields, such as neuroscience, high frequency finance and social media. So classic problems of classification and clustering are of increasing interest. However, analytic study of misclassification error probability in multi-class classification has barely begun. In this paper, we tackle the multi-class likelihood classification problem for point processes and develop, for the first time, both asymptotic upper and lower bounds on the error rate in terms of computable pair-wise affinities. We apply these general results to classifying renewal processes. Under some technical conditions, we show that the bounds have exponential decay and give explicit associated constants. The results are illustrated with a non-trivial simulation.

Pearson Distance is not a Distance

The Pearson distance between a pair of random variables $X,Y$ with correlation $\rho_{xy}$, namely, 1-$\rho_{xy}$, has gained widespread use, particularly for clustering, in areas such as gene expression analysis, brain imaging and cyber security. In all these applications it is implicitly assumed/required that the distance measures be metrics, thus satisfying the triangle inequality. We show however, that Pearson distance is not a metric. We go on to show that this can be repaired by recalling the result, (well known in other literature) that $\sqrt{1-\rho_{xy}}$ is a metric. We similarly show that a related measure of interest, $1-|\rho_{xy}|$, which is invariant to the sign of $\rho_{xy}$, is not a metric but that $\sqrt{1-\rho_{xy}^2}$ is. We also give generalizations of these results.