Bani K. Mallick

Graphical models are used to capture complex multivariate relationships and have applications in diverse disciplines such as biology, physics, and economics. Within this field, Gaussian graphical models aim to identify the pairs of variables whose dependence is maintained even after conditioning on the remaining variables in the data, known as the conditional dependence structure of the data. There are many existing software packages for Gaussian graphical modeling, however, they often make restrictive assumptions that reduce their flexibility for modeling data that are not identically distributed. Conversely, covdepGE is an R implementation of a variational weighted pseudo-likelihood algorithm for modeling the conditional dependence structure as a continuous function of an extraneous covariate. To build on the efficiency of this algorithm, covdepGE leverages parallelism and C++ integration with R. Additionally, covdepGE provides fully-automated and data-driven hyperparameter specification while maintaining flexibility for the user to decide key components of the estimation procedure. Through an extensive simulation study spanning diverse settings, covdepGE is demonstrated to be top of its class in recovering the ground truth conditional dependence structure while efficiently managing computational overhead.

The COVID-19 pandemic has profoundly reshaped human life. The development of COVID-19 vaccines has offered a semblance of normalcy. However, obstacles to vaccination have led to substantial loss of life and economic burdens. In this study, we analyze data from a prominent health insurance provider in the United States to uncover the underlying reasons behind the inability, refusal, or hesitancy to receive vaccinations. Our research proposes a methodology for pinpointing affected population groups and suggests strategies to mitigate vaccination barriers and hesitations. Furthermore, we estimate potential cost savings resulting from the implementation of these strategies. To achieve our objectives, we employed Bayesian data mining methods to streamline data dimensions and identify significant variables (features) influencing vaccination decisions. Comparative analysis reveals that the Bayesian method outperforms cutting-edge alternatives, demonstrating superior performance.

Sparse training has emerged as a promising method for resource-efficient deep neural networks (DNNs) in real-world applications. However, the reliability of sparse models remains a crucial concern, particularly in detecting unknown out-of-distribution (OOD) data. This study addresses the knowledge gap by investigating the reliability of sparse training from an OOD perspective and reveals that sparse training exacerbates OOD unreliability. The lack of unknown information and the sparse constraints hinder the effective exploration of weight space and accurate differentiation between known and unknown knowledge. To tackle these challenges, we propose a new unknown-aware sparse training method, which incorporates a loss modification, auto-tuning strategy, and a voting scheme to guide weight space exploration and mitigate confusion between known and unknown information without incurring significant additional costs or requiring access to additional OOD data. Theoretical insights demonstrate how our method reduces model confidence when faced with OOD samples. Empirical experiments across multiple datasets, model architectures, and sparsity levels validate the effectiveness of our method, with improvements of up to \textbf{8.4\%} in AUROC while maintaining comparable or higher accuracy and calibration. This research enhances the understanding and readiness of sparse DNNs for deployment in resource-limited applications. Our code is available on: \url{https://github.com/StevenBoys/MOON}.

Epidemiological studies have shown that circadian rhythm disruption (CRD) caused by shift work or frequent jet lag is associated with the risk of breast cancer development. However, the role of CRD in mammary gland morphology and aggressive mammary tumorigenesis and the molecular mechanisms underlying CRD and cancer risk remain unknown. We found that chronic CRD disrupted mouse mammary gland morphology and increased tumor burden and lung metastasis in a genetically engineered mouse model of aggressive breast cancer and induced an immunosuppressive tumor microenvironment by enhancing leukocyte immunoglobulin-like receptor 4a (LILRB4a or LILRB4) expression. Moreover, CRD increased the M2 macrophage (anti-inflammatory) and regulatory T-cell populations but decreased the M1 macrophage (proinflammatory) populations. These findings identify and implicate LILRB4a as a link between CRD and aggressive mammary tumorigenesis. Teaser Circadian rhythm disruption enhances aggressive mammary tumorigenesis by elevating LILRB4a expression.

Robust Bayesian methods for high-dimensional regression problems under diverse sparse regimes are studied. Traditional shrinkage priors are primarily designed to detect a handful of signals from tens of thousands of predictors in the so-called ultra-sparsity domain. However, they may not perform desirably when the degree of sparsity is moderate. In this paper, we propose a robust sparse estimation method under diverse sparsity regimes, which has a tail-adaptive shrinkage property. In this property, the tail-heaviness of the prior adjusts adaptively, becoming larger or smaller as the sparsity level increases or decreases, respectively, to accommodate more or fewer signals, a posteriori. We propose a global-local-tail (GLT) Gaussian mixture distribution that ensures this property. We examine the role of the tail-index of the prior in relation to the underlying sparsity level and demonstrate that the GLT posterior contracts at the minimax optimal rate for sparse normal mean models. We apply both the GLT prior and the Horseshoe prior to a real data problem and simulation examples. Our findings indicate that the varying tail rule based on the GLT prior offers advantages over a fixed tail rule based on the Horseshoe prior in diverse sparsity regimes.

This paper is concerned with explicitly modeling the effect of terrain on wind power curves. Terrain characteristics are spatially-varying but temporally constant, whereas other power curve-affiliating variables such wind speed, temperature, and wind power vary both spatially and temporally. In order to effectively model such two modes of variation in the data, we employ a Bayesian hierarchical model (BHM) that connects the terrain characteristics with the parameters in a power curve. BHM jointly models the data from all turbines on a wind farm for attaining the turbine-specific, terrain-incorporating power curves. Our analysis shows that, out of the three terrain variables available in our data, ruggedness has the strongest effect on the power curve. We also evaluate the applicability of using the resulting power curve model for turbines on a different terrain and find that incorporating terrain information explicitly is beneficial. The specific BHM mechanism of using terrain information leads to over 7–10% improvement over the group averaging approach.

Although sparse training has been successfully used in various resource-limited deep learning tasks to save memory, accelerate training, and reduce inference time, the reliability of the produced sparse models remains unexplored. Previous research has shown that deep neural networks tend to be over-confident, and we find that sparse training exacerbates this problem. Therefore, calibrating the sparse models is crucial for reliable prediction and decision-making. In this paper, we propose a new sparse training method to produce sparse models with improved confidence calibration. In contrast to previous research that uses only one mask to control the sparse topology, our method utilizes two masks, including a deterministic mask and a random mask. The former efficiently searches and activates important weights by exploiting the magnitude of weights and gradients. While the latter brings better exploration and finds more appropriate weight values by random updates. Theoretically, we prove our method can be viewed as a hierarchical variational approximation of a probabilistic deep Gaussian process. Extensive experiments on multiple datasets, model architectures, and sparsities show that our method reduces ECE values by up to 47.8\% and simultaneously maintains or even improves accuracy with only a slight increase in computation and storage burden.

The clustering of proteins is of interest in cancer cell biology. This article proposes a hierarchical Bayesian model for protein (variable) clustering hinging on correlation structure. Starting from a multivariate normal likelihood, we enforce the clustering through prior modeling using angle‐based unconstrained reparameterization of correlations and assume a truncated Poisson distribution (to penalize a large number of clusters) as prior on the number of clusters. The posterior distributions of the parameters are not in explicit form and we use a reversible jump Markov chain Monte Carlo based technique is used to simulate the parameters from the posteriors. The end products of the proposed method are estimated cluster configuration of the proteins (variables) along with the number of clusters. The Bayesian method is flexible enough to cluster the proteins as well as estimate the number of clusters. The performance of the proposed method has been substantiated with extensive simulation studies and one protein expression data with a hereditary disposition in breast cancer where the proteins are coming from different pathways.

Clustering of proteins is of interest in cancer cell biology. This article proposes a hierarchical Bayesian model for protein (variable) clustering hinging on correlation structure. Starting from a multivariate normal likelihood, we enforce the clustering through prior modeling using angle based unconstrained reparameterization of correlations and assume a truncated Poisson distribution (to penalize the large number of clusters) as prior on the number of clusters. The posterior distributions of the parameters are not in explicit form and we use a reversible jump Markov chain Monte Carlo (RJMCMC) based technique is used to simulate the parameters from the posteriors. The end products of the proposed method are estimated cluster configuration of the proteins (variables) along with the number of clusters. The Bayesian method is flexible enough to cluster the proteins as well as the estimate the number of clusters. The performance of the proposed method has been substantiated with extensive simulation studies and one protein expression data with a hereditary disposition in breast cancer where the proteins are coming from different pathways.