ABACUS: Unsupervised Multivariate Change Detection via Bayesian Source Separation
This addresses the challenge of detecting correlated changes in noisy multivariate data for applications like genomics and energy analysis, representing an incremental improvement with a novel hybrid approach.
The paper tackles the problem of unsupervised multivariate change detection for locating additive outliers and level shifts, proposing ABACUS, a Bayesian source separation method with multi-level sparsity, which shows competitive or superior performance in simulations against state-of-the-art methods and is applied to genomic profiles and electricity consumption data.
Change detection involves segmenting sequential data such that observations in the same segment share some desired properties. Multivariate change detection continues to be a challenging problem due to the variety of ways change points can be correlated across channels and the potentially poor signal-to-noise ratio on individual channels. In this paper, we are interested in locating additive outliers (AO) and level shifts (LS) in the unsupervised setting. We propose ABACUS, Automatic BAyesian Changepoints Under Sparsity, a Bayesian source separation technique to recover latent signals while also detecting changes in model parameters. Multi-level sparsity achieves both dimension reduction and modeling of signal changes. We show ABACUS has competitive or superior performance in simulation studies against state-of-the-art change detection methods and established latent variable models. We also illustrate ABACUS on two real application, modeling genomic profiles and analyzing household electricity consumption.