arXiv subjects

David S. Matteson

Publications and source records attributed to David S. Matteson.

At least 37 records · Page 2Linked to original sources

arXiv2022

Bayesian Spillover Graphs for Dynamic Networks

We present Bayesian Spillover Graphs (BSG), a novel method for learning temporal relationships, identifying critical nodes, and quantifying uncertainty for multi-horizon spillover effects in a dynamic system. BSG leverages both an interpretable framework via forecast error variance decompositions (FEVD) and comprehensive uncertainty quantification via Bayesian time series models to contextualize temporal relationships in terms of systemic risk and prediction variability. Forecast horizon hyperparameter $h$ allows for learning both short-term and equilibrium state network behaviors. Experiments for identifying source and sink nodes under various graph and error specifications show significant performance gains against state-of-the-art Bayesian Networks and deep-learning baselines. Applications to real-world systems also showcase BSG as an exploratory analysis tool for uncovering indirect spillovers and quantifying systemic risk.

stat.ME↗

arXiv2022

Interpretable Latent Variables in Deep State Space Models

We introduce a new version of deep state-space models (DSSMs) that combines a recurrent neural network with a state-space framework to forecast time series data. The model estimates the observed series as functions of latent variables that evolve non-linearly through time. Due to the complexity and non-linearity inherent in DSSMs, previous works on DSSMs typically produced latent variables that are very difficult to interpret. Our paper focus on producing interpretable latent parameters with two key modifications. First, we simplify the predictive decoder by restricting the response variables to be a linear transformation of the latent variables plus some noise. Second, we utilize shrinkage priors on the latent variables to reduce redundancy and improve robustness. These changes make the latent variables much easier to understand and allow us to interpret the resulting latent variables as random effects in a linear mixed model. We show through two public benchmark datasets the resulting model improves forecasting performances.

stat.ML↗

arXiv2022

Classifying Contaminated Cell Cultures using Time Series Features

We examine the use of time series data, derived from Electric Cell-substrate Impedance Sensing (ECIS), to differentiate between standard mammalian cell cultures and those infected with a mycoplasma organism. With the goal of interpretable results, we perform low-dimensional feature-based classification, extracting application-relevant features from the ECIS time courses. We can achieve very high classification accuracy using only two features, which depend on the cell line under examination. Initial results also show the existence of experimental variation between plates and suggest types of features that may prove more robust to such variation. Our paper is the first to perform a broad examination of ECIS time course features in the context of detecting contamination; to combine different types of features to achieve classification accuracy while preserving interpretability; and to describe and suggest possibilities for ameliorating plate-to-plate variation.

q-bio.QM↗

arXiv2021

Analysis of animal-related electric outages using species distribution models and community science data

Animal-related outages (AROs) are a prevalent form of outages in electrical distribution systems. Animal-infrastructure interactions vary across focal species and regions, underlining the need to study the animal-outage relationship in more species and diverse systems. Animal activity has been used as an indicator of reliability in the electrical grid system and to describe temporal patterns in AROs. However, these ARO models have been limited by a lack of available estimates of species activity, instead approximating activity based on seasonal and weather patterns in animal-related outage records and characteristics of broad taxonomic groups, e.g., squirrels. We highlight publicly available resources to fill the ecological data gap that is limiting joint analyses between ecology and energy sectors. Species distribution models (SDMs), a common technique to model the distribution of a species across geographic space and time, paired with data sourced from eBird, a community science database for bird observations, provided us with species-specific estimates of activity to model spatio-temporal patterns of AROs. These flexible, species-specific estimates can allow future animal-indicators of grid reliability to be investigated in more diverse regions and ecological communities, providing a better understanding of the variation that exists in animal-outage relationship. AROs were best modeled by accounting for multiple outage-prone species activity patterns and their unique relationships with seasonality and habitat availability. Different species were important for modeling outages in different landscapes and seasons depending on their distribution and migration behavior. We recommend that future models of AROs include species-specific activity data that account for the diverse spectrum of spatio-temporal activity patterns that outage-prone animals exhibit.

q-bio.OT↗

arXiv2021

Log-Gaussian Cox Process Modeling of Large Spatial Lightning Data using Spectral and Laplace Approximations

Lightning is a destructive and highly visible product of severe storms, yet there is still much to be learned about the conditions under which lightning is most likely to occur. The GOES-16 and GOES-17 satellites, launched in 2016 and 2018 by NOAA and NASA, collect a wealth of data regarding individual lightning strike occurrence and potentially related atmospheric variables. The acute nature and inherent spatial correlation in lightning data renders standard regression analyses inappropriate. Further, computational considerations are foregrounded by the desire to analyze the immense and rapidly increasing volume of lightning data. We present a new computationally feasible method that combines spectral and Laplace approximations in an EM algorithm, denoted SLEM, to fit the widely popular log-Gaussian Cox process model to large spatial point pattern datasets. In simulations, we find SLEM is competitive with contemporary techniques in terms of speed and accuracy. When applied to two lightning datasets, SLEM provides better out-of-sample prediction scores and quicker runtimes, suggesting its particular usefulness for analyzing lightning data, which tend to have sparse signals.

stat.AP↗

arXiv2021

Spatial Correlation in Weather Forecast Accuracy: A Functional Time Series Approach

A functional time series approach is proposed for investigating spatial correlation in daily maximum temperature forecast errors for 111 cities spread across the U.S. The modelling of spatial correlation is most fruitful for longer forecast horizons, and becomes less relevant as the forecast horizon shrinks towards zero. For 6-day-ahead forecasts, the functional approach uncovers interpretable regional spatial effects, and captures the higher variance observed in inland cities versus coastal cities, as well as the higher variance observed in mountain and midwest states. The functional approach also naturally handles missing data through modelling a continuum, and can be implemented efficiently by exploiting the sparsity induced by a B-spline basis. The temporal dependence in the data is modeled through temporal dependence in functional basis coefficients. Independent first order autoregressions with generalized autoregressive conditional heteroskedasticity [AR(1)+GARCH(1,1)] and Student-t innovations work well to capture the persistence of basis coefficients over time and the seasonal heteroskedasticity reflecting higher variance in winter. Through exploiting autocorrelation in the basis coefficients, the functional time series approach also yields a method for improving weather forecasts and uncertainty quantification. The resulting method corrects for bias in the weather forecasts, while reducing the error variance.

stat.ME↗

arXiv2021

Extended Missing Data Imputation via GANs for Ranking Applications

We propose Conditional Imputation GAN, an extended missing data imputation method based on Generative Adversarial Networks (GANs). The motivating use case is learning-to-rank, the cornerstone of modern search, recommendation system, and information retrieval applications. Empirical ranking datasets do not always follow standard Gaussian distributions or Missing Completely At Random (MCAR) mechanism, which are standard assumptions of classic missing data imputation methods. Our methodology provides a simple solution that offers compatible imputation guarantees while relaxing assumptions for missing mechanisms and sidesteps approximating intractable distributions to improve imputation quality. We prove that the optimal GAN imputation is achieved for Extended Missing At Random (EMAR) and Extended Always Missing At Random (EAMAR) mechanisms, beyond the naive MCAR. Our method demonstrates the highest imputation quality on the open-source Microsoft Research Ranking (MSR) Dataset and a synthetic ranking dataset compared to state-of-the-art benchmarks and across various feature distributions. Using a proprietary Amazon Search ranking dataset, we also demonstrate comparable ranking quality metrics for ranking models trained on GAN-imputed data compared to ground-truth data.

stat.ML↗

arXiv2021

IB-GAN: A Unified Approach for Multivariate Time Series Classification under Class Imbalance

Classification of large multivariate time series with strong class imbalance is an important task in real-world applications. Standard methods of class weights, oversampling, or parametric data augmentation do not always yield significant improvements for predicting minority classes of interest. Non-parametric data augmentation with Generative Adversarial Networks (GANs) offers a promising solution. We propose Imputation Balanced GAN (IB-GAN), a novel method that joins data augmentation and classification in a one-step process via an imputation-balancing approach. IB-GAN uses imputation and resampling techniques to generate higher quality samples from randomly masked vectors than from white noise, and augments classification through a class-balanced set of real and synthetic samples. Imputation hyperparameter $p_{miss}$ allows for regularization of classifier variability by tuning innovations introduced via generator imputation. IB-GAN is simple to train and model-agnostic, pairing any deep learning classifier with a generator-discriminator duo and resulting in higher accuracy for under-observed classes. Empirical experiments on open-source UCR data and proprietary 90K product dataset show significant performance gains against state-of-the-art parametric and GAN baselines.

stat.ML↗

arXiv2021

A Survey of Estimation Methods for Sparse High-dimensional Time Series Models

High-dimensional time series datasets are becoming increasingly common in many areas of biological and social sciences. Some important applications include gene regulatory network reconstruction using time course gene expression data, brain connectivity analysis from neuroimaging data, structural analysis of a large panel of macroeconomic indicators, and studying linkages among financial firms for more robust financial regulation. These applications have led to renewed interest in developing principled statistical methods and theory for estimating large time series models given only a relatively small number of temporally dependent samples. Sparse modeling approaches have gained popularity over the last two decades in statistics and machine learning for their interpretability and predictive accuracy. Although there is a rich literature on several sparsity inducing methods when samples are independent, research on the statistical properties of these methods for estimating time series models is still in progress. We survey some recent advances in this area, focusing on empirically successful lasso based estimation methods for two canonical multivariate time series models - stochastic regression and vector autoregression. We discuss key technical challenges arising in high-dimensional time series analysis and outline several interesting research directions.

stat.ME↗

arXiv2021

Graphical Influence Diagnostics for Changepoint Models

Changepoint models enjoy a wide appeal in a variety of disciplines to model the heterogeneity of ordered data. Graphical influence diagnostics to characterize the influence of single observations on changepoint models are, however, lacking. We address this gap by developing a framework for investigating instabilities in changepoint segmentations and assessing the influence of single observations on various outputs of a changepoint analysis. We construct graphical diagnostic plots that allow practitioners to assess whether instabilities occur; how and where they occur; and to detect influential individual observations triggering instability. We analyze well-log data to illustrate how such influence diagnostic plots can be used in practice to reveal features of the data that may otherwise remain hidden.

stat.ME↗

arXiv2021

Deep Denoising For Scientific Discovery: A Case Study In Electron Microscopy

Denoising is a fundamental challenge in scientific imaging. Deep convolutional neural networks (CNNs) provide the current state of the art in denoising natural images, where they produce impressive results. However, their potential has barely been explored in the context of scientific imaging. Denoising CNNs are typically trained on real natural images artificially corrupted with simulated noise. In contrast, in scientific applications, noiseless ground-truth images are usually not available. To address this issue, we propose a simulation-based denoising (SBD) framework, in which CNNs are trained on simulated images. We test the framework on data obtained from transmission electron microscopy (TEM), an imaging technique with widespread applications in material science, biology, and medicine. SBD outperforms existing techniques by a wide margin on a simulated benchmark dataset, as well as on real data. Apart from the denoised images, SBD generates likelihood maps to visualize the agreement between the structure of the denoised image and the observed data. Our results reveal shortcomings of state-of-the-art denoising architectures, such as their small field-of-view: substantially increasing the field-of-view of the CNNs allows them to exploit non-local periodic patterns in the data, which is crucial at high noise levels. In addition, we analyze the generalization capability of SBD, demonstrating that the trained networks are robust to variations of imaging parameters and of the underlying signal structure. Finally, we release the first publicly available benchmark dataset of TEM images, containing 18,000 examples.

cs.CV↗

arXiv2021

Critical Risk Indicators (CRIs) for the electric power grid: A survey and discussion of interconnected effects

The electric power grid is a critical societal resource connecting multiple infrastructural domains such as agriculture, transportation, and manufacturing. The electrical grid as an infrastructure is shaped by human activity and public policy in terms of demand and supply requirements. Further, the grid is subject to changes and stresses due to solar weather, climate, hydrology, and ecology. The emerging interconnected and complex network dependencies make such interactions increasingly dynamic causing potentially large swings, thus presenting new challenges to manage the coupled human-natural system. This paper provides a survey of models and methods that seek to explore the significant interconnected impact of the electric power grid and interdependent domains. We also provide relevant critical risk indicators (CRIs) across diverse domains that may influence electric power grid risks, including climate, ecology, hydrology, finance, space weather, and agriculture. We discuss the convergence of indicators from individual domains to explore possible systemic risk, i.e., holistic risk arising from cross-domains interconnections. Our study provides an important first step towards data-driven analysis and predictive modeling of risks in the coupled interconnected systems. Further, we propose a compositional approach to risk assessment that incorporates diverse domain expertise and information, data science, and computer science to identify domain-specific CRIs and their union in systemic risk indicators.

stat.AP↗

arXiv2021

Sparse Identification and Estimation of Large-Scale Vector AutoRegressive Moving Averages

The Vector AutoRegressive Moving Average (VARMA) model is fundamental to the theory of multivariate time series; however, identifiability issues have led practitioners to abandon it in favor of the simpler but more restrictive Vector AutoRegressive (VAR) model. We narrow this gap with a new optimization-based approach to VARMA identification built upon the principle of parsimony. Among all equivalent data-generating models, we use convex optimization to seek the parameterization that is "simplest" in a certain sense. A user-specified strongly convex penalty is used to measure model simplicity, and that same penalty is then used to define an estimator that can be efficiently computed. We establish consistency of our estimators in a double-asymptotic regime. Our non-asymptotic error bound analysis accommodates both model specification and parameter estimation steps, a feature that is crucial for studying large-scale VARMA algorithms. Our analysis also provides new results on penalized estimation of infinite-order VAR, and elastic net regression under a singular covariance structure of regressors, which may be of independent interest. We illustrate the advantage of our method over VAR alternatives on three real data examples.

stat.ME↗

arXiv2021

Developing and Evaluating Deep Neural Network-based Denoising for Nanoparticle TEM Images with Ultra-low Signal-to-Noise

A deep convolutional neural network has been developed to denoise atomic-resolution TEM image datasets of nanoparticles acquired using direct electron counting detectors, for applications where the image signal is severely limited by shot noise. The network was applied to a model system of CeO2-supported Pt nanoparticles. We leverage multislice image simulations to generate a large and flexible dataset for training and testing the network. The proposed network outperforms state-of-the-art denoising methods by a significant margin both on simulated and experimental test data. Factors contributing to the performance are identified, including most importantly (a) the geometry of the images used during training and (b) the size of the network's receptive field. Through a gradient-based analysis, we investigate the mechanisms learned by the network to denoise experimental images. This shows that the network exploits global and local information in the noisy measurements, for example, by adapting its filtering approach when it encounters atomic-level defects at the nanoparticle surface. Extensive analysis has been done to characterize the network's ability to correctly predict the exact atomic structure at the nanoparticle surface. Finally, we develop an approach based on the log-likelihood ratio test that provides a quantitative measure of the agreement between the noisy observation and the atomic-level structure in the network-denoised image.

cond-mat.mtrl-sci↗

arXiv2021

Graph-Based Continual Learning

Despite significant advances, continual learning models still suffer from catastrophic forgetting when exposed to incrementally available data from non-stationary distributions. Rehearsal approaches alleviate the problem by maintaining and replaying a small episodic memory of previous samples, often implemented as an array of independent memory slots. In this work, we propose to augment such an array with a learnable random graph that captures pairwise similarities between its samples, and use it not only to learn new tasks but also to guard against forgetting. Empirical results on several benchmark datasets show that our model consistently outperforms recently proposed baselines for task-free continual learning.

stat.ML↗

arXiv2021

Group Linear non-Gaussian Component Analysis with Applications to Neuroimaging

Independent component analysis (ICA) is an unsupervised learning method popular in functional magnetic resonance imaging (fMRI). Group ICA has been used to search for biomarkers in neurological disorders including autism spectrum disorder and dementia. However, current methods use a principal component analysis (PCA) step that may remove low-variance features. Linear non-Gaussian component analysis (LNGCA) enables simultaneous dimension reduction and feature estimation including low-variance features in single-subject fMRI. We present a group LNGCA model to extract group components shared by more than one subject and subject-specific components. To determine the total number of components in each subject, we propose a parametric resampling test that samples spatially correlated Gaussian noise to match the spatial dependence observed in data. In simulations, our estimated group components achieve higher accuracy compared to group ICA. We apply our method to a resting-state fMRI study on autism spectrum disorder in 342 children (252 typically developing, 90 with autism), where the group signals include resting-state networks. We find examples of group components that appear to exhibit different levels of temporal engagement in autism versus typically developing children, as revealed using group LNGCA. This novel approach to matrix decomposition is a promising direction for feature detection in neuroimaging.

stat.ME↗

arXiv2020

Regularized Estimation in High-Dimensional Vector Auto-Regressive Models using Spatio-Temporal Information

A Vector Auto-Regressive (VAR) model is commonly used to model multivariate time series, and there are many penalized methods to handle high dimensionality. However in terms of spatio-temporal data, most methods do not take the spatial and temporal structure of the data into consideration, which may lead to unreliable network detection and inaccurate forecasts. This paper proposes a data-driven weighted l1 regularized approach for spatio-temporal VAR model. Extensive simulation studies are carried out to compare the proposed method with four existing methods of high-dimensional VAR model, demonstrating improvements of our method over others in parameter estimation, network detection and out-of-sample forecasts. We also apply our method on a traffic data set to evaluate its performance in real application. In addition, we explore the theoretical properties of l1 regularized estimation of VAR model under the weakly sparse scenario, in which the exact sparsity can be viewed as a special case. To the best of our knowledge, this direction has not been considered yet in the literature. For general stationary VAR process, we derive the non-asymptotic upper bounds on l1 regularized estimation errors under the weakly sparse scenario, provide the conditions of estimation consistency, and further simplify these conditions for a special VAR(1) case.

stat.ME↗

arXiv2020

Modeling a Nonlinear Biophysical Trend Followed by Long-Memory Equilibrium with Unknown Change Point

Measurements of many biological processes are characterized by an initial trend period followed by an equilibrium period. Scientists may wish to quantify features of the two periods, as well as the timing of the change point. Specifically, we are motivated by problems in the study of electrical cell-substrate impedance sensing (ECIS) data. ECIS is a popular new technology which measures cell behavior non-invasively. Previous studies using ECIS data have found that different cell types can be classified by their equilibrium behavior. However, it can be challenging to identify when equilibrium has been reached, and to quantify the relevant features of cells' equilibrium behavior. In this paper, we assume that measurements during the trend period are independent deviations from a smooth nonlinear function of time, and that measurements during the equilibrium period are characterized by a simple long memory model. We propose a method to simultaneously estimate the parameters of the trend and equilibrium processes and locate the change point between the two. We find that this method performs well in simulations and in practice. When applied to ECIS data, it produces estimates of change points and measures of cell equilibrium behavior which offer improved classification of infected and uninfected cells.

stat.AP↗