A distributed framework for reducing high-dimensional matrix-variate time series data.
problem Reducing dimensionality of high-dimensional, heterogeneous matrix-variate time series data.
method Data partitioning, distributed two-dimensional tensor PCA, aggregation, final PCA, factor matrix computation.
result Preserves latent matrix structure, improves computational efficiency and information utilization.
New method clusters matrix-variate data with outliers.
problem Clustering matrix-variate data with outliers.
method Iterative approach using subset log-likelihoods.
result Extends OCLUST algorithm to matrix-variate normal data.
Matrix-variate distributions can intuitively model the dependence structure of matrix-valued observations that arise in applications with multivariate time series, spatio-temporal or repeated measures. This paper develops an Expectation-Maximization algorithm for discriminant analysis and classification with matrix-var…
New method infers graph from dependent matrix data.
problem Inferring graph from dependent matrix data.
method Sparse-group lasso-based frequency-domain formulation with ADMM approach.
result Local convergence of inverse PSD estimators to true value.
In recent years, data have become increasingly higher dimensional and, therefore, an increased need has arisen for dimension reduction techniques for clustering. Although such techniques are firmly established in the literature for multivariate data, there is a relative paucity in the area of matrix variate, or three-w…
This paper develops a Bayesian procedure for estimation and forecasting of the volatility of multivariate time series. The foundation of this work is the matrix-variate dynamic linear model, for the volatility of which we adopt a multiplicative stochastic evolution, using Wishart and singular multivariate beta distribu…
We consider a statistical model for pairs of traded assets, based on a Cointegrated Vector Auto Regression (CVAR) Model. We extend standard CVAR models to incorporate estimation of model parameters in the presence of price series level shifts which are not accurately modeled in the standard Gaussian error correction mo…
Over the years data has become increasingly higher dimensional, which has prompted an increased need for dimension reduction techniques. This is perhaps especially true for clustering (unsupervised classification) as well as semi-supervised and supervised classification. Although dimension reduction in the area of clus…
Estimates covariance matrices for matrix-variate data via core covariance geometry.
problem Estimating covariance matrices for matrix-variate data with partial isotropy.
method Fixed-rank core covariance geometry, partial-isotropy rank-r core shrinkage estimator.
result The geometry of the space of rank-r cores is a smooth manifold.
Undirected graphs can be used to describe matrix variate distributions. In this paper, we develop new methods for estimating the graphical structures and underlying parameters, namely, the row and column covariance and inverse covariance matrices from the matrix variate data. Under sparsity conditions, we show that one…
Online graph learning from matrix-valued time series data.
problem Identifying dependency structure among sensors in a network.
method Extends VAR models to matrix-variate models, proposes online procedures for graph learning, and introduces Lasso-type approaches.
result Demonstrates effectiveness of online graph learning methods in both synthetic and real data.
We propose a novel hierarchical model for multitask bipartite ranking. The proposed approach combines a matrix-variate Gaussian process with a generative model for task-wise bipartite ranking. In addition, we employ a novel trace constrained variational inference approach to impose low rank structure on the posterior m…
This paper develops a matrix-variate adaptive Markov chain Monte Carlo (MCMC) methodology for Bayesian Cointegrated Vector Auto Regressions (CVAR). We replace the popular approach to sampling Bayesian CVAR models, involving griddy Gibbs, with an automated efficient alternative, based on the Adaptive Metropolis algorith…
Variational Bayesian neural networks combine the flexibility of deep learning with Bayesian uncertainty estimation. However, inference procedures for flexible variational posteriors are computationally expensive. A recently proposed method, noisy natural gradient, is a surprisingly simple method to fit expressive poste…
This paper proposes robust matrix variate regression models with rank constraints and vector regularization.
problem High dimensional and noisy matrix-valued predictors in regression models.
method Rank constraint, vector regularization, alternating projected gradient descent algorithm.
result The proposed method achieves the minimax rate of estimation errors.
Transposable data represents interactions among two sets of entities, and are typically represented as a matrix containing the known interaction values. Additional side information may consist of feature vectors specific to entities corresponding to the rows and/or columns of such a matrix. Further information may also…
We face network data from various sources, such as protein interactions and online social networks. A critical problem is to model network interactions and identify latent groups of network nodes. This problem is challenging due to many reasons. For example, the network nodes are interdependent instead of independent o…
Enhances traffic forecasting with dynamic regression incorporating error modeling.
problem Improving accuracy of traffic forecasts using deep spatiotemporal models.
method Integrates matrix-variate autoregressive (AR) model into loss function for error series of base model.
result Improved traffic forecasting performance on SOTA models with interpretable AR coefficients.
MMM model clusters mixed-type longitudinal data efficiently.
problem Challenges in clustering multivariate longitudinal mixed-type data.
method MMM model reorganizes data into a three-way structure, using a mixture of matrix-variate normal distributions.
result MMM model handles various data types (continuous, ordinal, binary, nominal, count) and temporal dependence.
A parsimonious model reduces over-parameterization in skewed matrix variate mixtures.
problem Over-parameterization in skewed matrix variate mixtures.
method Parsimonious family of 256 models using bilinear factor analyzers constrained over clusters, with AECM algorithm for estimation.
result Extensive simulations and real-world datasets (MNIST, Olivetti faces) demonstrate the method's effectiveness.
Gaussian process model for vector-valued function has been shown to be useful for multi-output prediction. The existing method for this model is to re-formulate the matrix-variate Gaussian distribution as a multivariate normal distribution. Although it is effective in many cases, re-formulation is not always workable a…
Paper finds a lower bound for estimating low-rank matrices in logistic regression.
problem Estimating low-rank coefficient matrices in logistic regression.
method Derives a minimax lower bound on the risk.
result The bound depends on matrix dimensions, rank, and sample size.
The key idea of variational auto-encoders (VAEs) resembles that of traditional auto-encoder models in which spatial information is supposed to be explicitly encoded in the latent space. However, the latent variables in VAEs are vectors, which can be interpreted as multiple feature maps of size 1x1. Such representations…
Proposes a robust factor analysis for matrix data.
problem Robust factor analysis for matrix data with heavy-tailed or contaminated data.
method Bilinear factor analysis based on the matrix-variate t distribution. result Significantly higher breakdown point than traditional methods.
Cluster analysis is a fundamental tool for pattern discovery of complex heterogeneous data. Prevalent clustering methods mainly focus on vector or matrix-variate data and are not applicable to general-order tensors, which arise frequently in modern scientific and business applications. Moreover, there is a gap between …
Missing data estimation is an important challenge with high-dimensional data arranged in the form of a matrix. Typically this data matrix is transposable, meaning that either the rows, columns or both can be treated as features. To model transposable data, we present a modification of the matrix-variate normal, the mea…
Differential privacy mechanism design has traditionally been tailored for a scalar-valued query function. Although many mechanisms such as the Laplace and Gaussian mechanisms can be extended to a matrix-valued query function by adding i.i.d. noise to each element of the matrix, this method is often suboptimal as it for…
It has been proposed that complex populations, such as those that arise in genomics studies, may exhibit dependencies among observations as well as among variables. This gives rise to the challenging problem of analyzing unreplicated high-dimensional data with unknown mean and dependence structures. Matrix-variate appr…
RFPCA improves robustness of FPCA for matrix data.
problem Outliers in matrix data degrade the performance of FPCA.
method RFPCA uses matrix-variate t-distribution and EM algorithm for robust estimation.
result RFPCA outperforms other methods in detecting matrix-valued outliers.
This text investigates relations between two well-known family of algorithms, matrix factorisations and recursive linear filters, by describing a probabilistic model in which approximate inference corresponds to a matrix factorisation algorithm. Using the probabilistic model, we derive a matrix factorisation algorithm …
Ordinal data is omnipresent in almost all multiuser-generated feedback - questionnaires, preferences etc. This paper investigates modelling of ordinal data with Gaussian restricted Boltzmann machines (RBMs). In particular, we present the model architecture, learning and inference procedures for both vector-variate and …
New distribution simplifies covariance matrix inference.
problem Efficient inference for covariance matrices in large models.
method Incorporates Inverse G-Wishart distribution for variational message passing.
result Elegant and succinct expression of variational message passing fragments.
New algorithm estimates matrix-valued regression parameters efficiently.
problem High-dimensional matrix regression with limited sample size.
method KRO-PRO-FAC algorithm using Kronecker product factorization.
result Algorithm provides accurate parameter estimates without covariance estimation.
The explosion of time series data in recent years has brought a flourish of new time series analysis methods, for forecasting, clustering, classification and other tasks. The evaluation of these new methods requires either collecting or simulating a diverse set of time series benchmarking data to enable reliable compar…
Previous studies indicate that nonlinear properties of Gaussian time series with long-range correlations, ui, can be detected and quantified by studying the correlations in the magnitude series ∣ui∣, i.e., the ``volatility''. However, the origin for this empirical observation still remains unclear, and the exact …
Research into time series classification has tended to focus on the case of series of uniform length. However, it is common for real-world time series data to have unequal lengths. Differing time series lengths may arise from a number of fundamentally different mechanisms. In this work, we identify and evaluate two cla…
Modeling regime shifts in co-evolving time series with interactions and time-dependency.
problem Discovering and modeling regime shifts in multiple time series with relationships and time-dependent behaviors.
method Modeling interactions and time-dependency in co-evolving time series using a mapping grid and dynamic network representation for regime identification and time-dependent Cox regression for regime transition probabilities.
result A principled approach for modeling interactions and time-dependency in co-evolving time series.
MDF represents time series motifs as images for improved classification.
problem Classifying time series data with high-order patterns.
method Motif Difference Field (MDF) using Fully Convolutional Networks (FCN).
result MDF outperforms other methods on UCR time series datasets.
We provide the proof that the space of time series data is a Kolmogorov space with T0-separation axiom using the loop space of time series data. In our approach we define a cyclic coordinate of intrinsic time scale of time series data after empirical mode decomposition. A spinor field of time series data comes fro…
Capturing the dynamical properties of time series concisely as interpretable feature vectors can enable efficient clustering and classification for time-series applications across science and industry. Selecting an appropriate feature-based representation of time series for a given application can be achieved through s…
Overview of high-dimensional time series regression methods.
problem Estimation and inference with high-dimensional time series data.
method Limit theory for high-dimensional dependent data, asymptotic theory for time series regression, statistical learning methods.
result Main limit theory results and asymptotic theory for high-dimensional time series regression.
New method uses Transformers for flu forecasting.
problem Forecasting influenza-like illness trends.
method Transformer-based machine learning models with self-attention.
result Forecasting results are competitive with state-of-the-art methods.
Improved prediction of hierarchical time series using structured regularization.
problem Making coherent forecasts for hierarchical time series.
method Structured regularization method for bottom-level time series predictions.
result Superior prediction accuracy and computational efficiency compared to previous methods.
Introduces a new benchmark for time series extrinsic regression.
problem Predicting a single continuous value from univariate or multivariate time series, not necessarily related to the predictor.
method Developed a new benchmarking archive for time series extrinsic regression.
result Initial benchmarking of existing models on the new TSER datasets.
Few-shot learning improves time-series forecasting with limited data.
problem Limited data in target tasks degrade forecasting performance.
method A few-shot learning method using recurrent neural networks with attention.
result The model forecasts future values effectively with minimal data.
Meta-learning for Koopman spectral analysis with short time-series data.
problem Lack of long time-series for training embedding functions in Koopman spectral analysis.
method Meta-learning approach using bidirectional LSTM and neural network to estimate embedding functions from short time-series.
result The proposed method achieves better performance in eigenvalue estimation and future prediction compared to existing methods.
Transformers improve time series modeling by capturing long-range dependencies.
problem Capturing long-range dependencies in time series data.
method Summarized and reviewed adaptations of Transformers for time series analysis.
result Transformers enhance time series forecasting, anomaly detection, and classification.
Archive of 20 time series datasets for forecasting evaluation.
problem Lack of comprehensive time series forecasting datasets.
method Compilation and characterisation of 20 datasets from various domains.
result Characterisation and performance evaluation of datasets.