arXiv subjects

Tapabrata Maiti

Publications and source records attributed to Tapabrata Maiti.

27 records · Page 2Linked to original sources

arXiv2020

Ultra high dimensional generalized additive model: Unified Theory and Methods

Generalized additive model is a powerful statistical learning and predictive modeling tool that has been applied in a wide range of applications. The need of high-dimensional additive modeling is eminent in the context of dealing with high through-put data such as genetic data analysis. In this article, we studied a two step selection and estimation method for ultra high dimensional generalized additive models. The first step applies group lasso on the expanded bases of the functions. With high probability this selects all nonzero functions without having too much over selection. The second step uses adaptive group lasso with any initial estimators, including the group lasso estimator, that satisfies some regular conditions. The adaptive group lasso estimator is shown to be selection consistent with improved convergence rates. Tuning parameter selection is also discussed and shown to select the true model consistently under GIC procedure. The theoretical properties are supported by extensive numerical study.

stat.ME↗

arXiv2020

Statistical Foundation of Variational Bayes Neural Networks

Despite the popularism of Bayesian neural networks in recent years, its use is somewhat limited in complex and big data situations due to the computational cost associated with full posterior evaluations. Variational Bayes (VB) provides a useful alternative to circumvent the computational cost and time complexity associated with the generation of samples from the true posterior using Markov Chain Monte Carlo (MCMC) techniques. The efficacy of the VB methods is well established in machine learning literature. However, its potential broader impact is hindered due to a lack of theoretical validity from a statistical perspective. However there are few results which revolve around the theoretical properties of VB, especially in non-parametric problems. In this paper, we establish the fundamental result of posterior consistency for the mean-field variational posterior (VP) for a feed-forward artificial neural network model. The paper underlines the conditions needed to guarantee that the VP concentrates around Hellinger neighborhoods of the true density function. Additionally, the role of the scale parameter and its influence on the convergence rates has also been discussed. The paper mainly relies on two results (1) the rate at which the true posterior grows (2) the rate at which the KL-distance between the posterior and variational posterior grows. The theory provides a guideline of building prior distributions for Bayesian NN models along with an assessment of accuracy of the corresponding VB implementation.

stat.ML↗

arXiv2020

High Dimensional Classification for Spatially Dependent Data with Application to Neuroimaging

Discriminating patients with Alzheimer's disease (AD) from healthy subjects is a crucial task in the research of Alzheimer's disease. The task can be potentially achieved by linear discriminant analysis (LDA), which is one of the most classical and popular classification techniques. However, the classification problem becomes challenging for LDA because of the high-dimensionally and the spatial dependency of the brain imaging data. To address the challenges, researchers have proposed various ways to generalize LDA into high-dimensional context in recent years. However, these existing methods did not reach any consensus on how to incorporate spatially dependent structure. In light of the current needs and limitations, we propose a new classification method, named as Penalized Maximum Likelihood Estimation LDA (PMLE-LDA). The proposed method uses $Mat\acute{e}rn$ covariance function to describe the spatial correlation of brain regions. Additionally, PMLE is designed to model the sparsity of high-dimensional features. The spatial location information is used to address the singularity of the covariance. Tapering technique is introduced to reduce computational burden. We show in theory that the proposed method can not only provide consistent results of parameter estimation and feature selection, but also generate an asymptotically optimal classifier driven by high dimensional data with specific spatially dependent structure. Finally, the method is validated through simulations and an application into ADNI data for classifying Alzheimer's patients.

stat.ME↗

arXiv2018

Uncertainty Estimation in Functional Linear Models

Functional data analysis is proved to be useful in many scientific applications. The physical process is observed as curves and often there are several curves observed due to multiple subjects, providing the replicates in statistical sense. The recent literature develops several techniques for registering the curves and associated model estimation. However, very little has been investigated for statistical inference, specifically uncertainty estimation. In this article, we consider functional linear mixed modeling approach to combine several curves. We concentrate measuring uncertainty when the functional linear mixed models are used for prediction. Although measuring the uncertainty is paramount interest in any statistical prediction, there is no closed form expression available for functional mixed effects models. In many real life applications only a finite number of curves can be observed. In such situations it is important to asses the error rate for any valid statistical statement. We derive theoretically valid approximation of uncertainty measurements that are suitable along with modified estimation techniques. We illustrate our methods by numerical examples and compared with other existing literature as appropriate. Our method is computationally simple and often outperforms the other methods.

stat.ME↗

arXiv2016

Spatial Clustering of Curves with Functional Covariates: A Bayesian Partitioning Model with Application to Spectra Radiance in Climate Study

In climate change study, the infrared spectral signatures of climate change have recently been conceptually adopted, and widely applied to identifying and attributing atmospheric composition change. We propose a Bayesian hierarchical model for spatial clustering of the high-dimensional functional data based on the effects of functional covariates and local features. We couple the functional mixed-effects model with a generalized spatial partitioning method for: (1) producing spatially contiguous clusters for the high-dimensional spatio-functional data; (2) improving the computational efficiency via parallel computing over subregions or multi-level partitions; and (3) capturing the near-boundary ambiguity and uncertainty for data-driven partitions. We propose a generalized partitioning method which puts less constraints on the shape of spatial clusters. Dimension reduction in the parameter space is also achieved via Bayesian wavelets to alleviate the increasing model complexity introduced by clusters. The model well captures the regional effects of the atmospheric and cloud properties on the spectral radiance measurements. The results elaborate the importance of exploiting spatially contiguous partitions for identifying regional effects and small-scale variability.

stat.AP↗

arXiv2014

A generalized mixed model framework for assessing fingerprint individuality in presence of varying image quality

Fingerprint individuality refers to the extent of uniqueness of fingerprints and is the main criteria for deciding between a match versus nonmatch in forensic testimony. Often, prints are subject to varying levels of noise, for example, the image quality may be low when a print is lifted from a crime scene. A poor image quality causes human experts as well as automatic systems to make more errors in feature detection by either missing true features or detecting spurious ones. This error lowers the extent to which one can claim individualization of fingerprints that are being matched. The aim of this paper is to quantify the decrease in individualization as image quality degrades based on fingerprint images in real databases. This, in turn, can be used by forensic experts along with their testimony in a court of law. An important practical concern is that the databases used typically consist of a large number of fingerprint images so computational algorithms such as the Gibbs sampler can be extremely slow. We develop algorithms based on the Laplace approximation of the likelihood and infer the unknown parameters based on this approximate likelihood. Two publicly available databases, namely, FVC2002 and FVC2006, are analyzed from which estimates of individuality are obtained. From a statistical perspective, the contribution can be treated as an innovative application of Generalized Linear Mixed Models (GLMMs) to the field of fingerprint-based authentication.

stat.AP↗

arXiv2006

Nonparametric estimation of mean-squared prediction error in nested-error regression models

Nested-error regression models are widely used for analyzing clustered data. For example, they are often applied to two-stage sample surveys, and in biology and econometrics. Prediction is usually the main goal of such analyses, and mean-squared prediction error is the main way in which prediction performance is measured. In this paper we suggest a new approach to estimating mean-squared prediction error. We introduce a matched-moment, double-bootstrap algorithm, enabling the notorious underestimation of the naive mean-squared error estimator to be substantially reduced. Our approach does not require specific assumptions about the distributions of errors. Additionally, it is simple and easy to apply. This is achieved through using Monte Carlo simulation to implicitly develop formulae which, in a more conventional approach, would be derived laboriously by mathematical arguments.

math.ST↗

arXiv2006

Resampling Based Empirical Prediction: An Application to Small Area Estimation

Best linear unbiased prediction is well known for its wide range of applications including small area estimation. While the theory is well established for mixed linear models and under normality of the error and mixing distributions, the literature is sparse for nonlinear mixed models under nonnormality of the error or of the mixing distributions. This article develops a resampling based unified approach for predicting mixed effects under a generalized mixed model set up. Second order accurate nonnegative estimators of mean squared prediction errors are also developed. Given the parametric model, the proposed methodology automatically produces estimates of the small area parameters and their MSPEs, without requiring explicit analytical expressions for the MSPE.

math.ST↗

arXiv2006

Nonnegative mean squared prediction error estimation in small area estimation

Small area estimation has received enormous attention in recent years due to its wide range of application, particularly in policy making decisions. The variance based on direct sample size of small area estimator is unduly large and there is a need of constructing model based estimator with low mean squared prediction error (MSPE). Estimation of MSPE and in particular the bias correction of MSPE plays the central piece of small area estimation research. In this article, a new technique of bias correction for the estimated MSPE is proposed. It is shown that that the new MSPE estimator attains the same level of bias correction as the existing estimators based on straight Taylor expansion and jackknife methods. However, unlike the existing methods, the proposed estimate of MSPE is always nonnegative. Furthermore, the proposed method can be used for general two-level small area models where the variables at each level can be discrete or continuous and, in particular, be nonnormal.

math.ST↗