For the challenging task of modeling multivariate time series, we propose a new class of models that use dependent Mat ern processes to capture the underlying structure of data, explain their interdependencies, and predict their unknown values. Although similar models have been proposed in the econometric, statistics, and machine learning literature, our approach has several advantages that distinguish it from existing methods: 1) it is flexible to provide high prediction accuracy, yet its complexity is controlled to avoid overfitting; 2) its interpretability separates it from black-box methods; 3) finally, its computational efficiency makes it scalable for high-dimensional time series. In this paper, we use several simulated and real data sets to illustrate these advantages. We will also briefly discuss some extensions of our model.

We reframe linear dimensionality reduction as a problem of Bayesian inference on matrix manifolds. This natural paradigm extends the Bayesian framework to dimensionality reduction tasks in higher dimensions with simpler models at greater speeds. Here an orthogonal basis is treated as a single point on a manifold and is associated with a linear subspace on which observations vary maximally. Throughout this paper, we employ the Grassmann and Stiefel manifolds for various dimensionality reduction problems, explore the connection between the two manifolds, and use Hybrid Monte Carlo for posterior sampling on the Grassmannian for the first time. We delineate in which situations either manifold should be considered. Further, matrix manifold models are used to yield scientific insight in the context of cognitive neuroscience, and we conclude that our methods are suitable for basic inference as well as accurate prediction.

Neuroscientists are increasingly collecting multimodal data during experiments and observational studies. Different data modalities-such as EEG, fMRI, LFP, and spike trains-offer different views of the complex systems contributing to neural phenomena. Here, we focus on joint modeling of LFP and spike train data, and present a novel Bayesian method for neural decoding to infer behavioral and experimental conditions. This model performs supervised dual-dimensionality reduction: it learns low-dimensional representations of two different sources of information that not only explain variation in the input data itself, but also predict extra-neuronal outcomes. Despite being one probabilistic unit, the model consists of multiple modules: exponential PCA and wavelet PCA are used for dimensionality reduction in the spike train and LFP modules, respectively; these modules simultaneously interface with a Bayesian binary regression module. We demonstrate how this model may be used for prediction, parametric inference, and identification of influential predictors. In prediction, the hierarchical model outperforms other models trained on LFP alone, spike train alone, and combined LFP and spike train data. We compare two methods for modeling the loading matrix and find them to perform similarly. Finally, model parameters and their posterior distributions yield scientific insights.

We present geodesic Lagrangian Monte Carlo, an extension of Hamiltonian Monte Carlo for sampling from posterior distributions defined on general Riemannian manifolds. We apply this new algorithm to Bayesian inference on symmetric or Hermitian positive definite matrices. To do so, we exploit the Riemannian structure induced by Cartan's canonical metric. The geodesics that correspond to this metric are available in closed-form and-within the context of Lagrangian Monte Carlo-provide a principled way to travel around the space of positive definite matrices. Our method improves Bayesian inference on such matrices by allowing for a broad range of priors, so we are not limited to conjugate priors only. In the context of spectral density estimation, we use the (non-conjugate) complex reference prior as an example modeling option made available by the algorithm. Results based on simulated and real-world multivariate time series are presented in this context, and future directions are outlined.

We are interested in survival analysis of hemodialysis patients for whom several biomarkers are recorded over time. Motivated by this challenging problem, we propose a general framework for multivariate joint longitudinal-survival modeling that can be used to examine the association between several longitudinally recorded covariates and a time-to-event endpoint. Our method allows for simultaneous modeling of longitudinal covariates by taking their correlation into account. This leads to a more efficient method for modeling their trajectories over time, and hence, it can better capture their relationship to the survival outcomes.

Nuisance flooding corresponds to minor and frequent flood events that have significant socioeconomic and public health impacts on coastal communities. Yearly averaged local mean sea level can be used as proxy to statistically predict the impacts of sea level rise (SLR) on the frequency of nuisance floods (NFs). In this study, we use generalized linear models (GLM) and Gaussian Process (GP) models combined to (i) estimate the frequency of NF associated with the change in mean sea level, and (ii) quantify the associated uncertainties via a novel and statistically robust approach. We calibrate our models to the water level data from 18 tide gauges along the coasts of United States, and after validation, we estimate the frequency of NF associated with the SLR projections in year 2030 (under RCPs 2.6 and 8.5), along with their 90% bands, at each gauge. The historical NF-SLR data are very noisy, and show large changes in variability (heteroscedasticity) with SLR. Prior models in the literature do not properly account for the observed heteroscedasticity, and thus their projected uncertainties are highly suspect. Among the models used in this study, the Negative Binomial Distribution GLM with GP best characterizes the uncertainties associated with NF estimates; on validation data (Formula presented.) 93% of the points fall within the 90% credible limit, showing our approach to be a robust model for uncertainty quantification.