Research

My research focuses on methodological, computational, and theoretical aspects of modern Bayesian statistics & probabilistic machine learning. I greatly enjoy the interdisciplinary nature of statistics and the opportunity to interact and collaborate with domain experts, and simultaneously strive to identify challenging foundational questions stemming from interesting applied problems and provide rigorous mathematical solutions. Some representative publications are listed below, grouped by areas of interest. See my google scholar profile here for the most updated list of publications.


Bayesian high-dimensional shrinkage priors: theory and methods

  1. A mass-shifting phenomenon of truncated multivariate normal priors

S. Zhou, P. Ray, D. Pati, and A. Bhattacharya. Under revision.

  1. Functional horseshoe priors for subspace shrinkage.

M. Shin, A. Bhattacharya, and V. E. Johnson. Journal of the American Statistical Association (2020)

  1. Bayesian sparse multiple regression for simultaneous rank reduction and variable selection

A. Chakraborty, A. Bhattacharya, and B. K. Mallick. Biometrika (2020)

  1. Dirichlet-Laplace priors for optimal shrinkage

A. Bhattacharya, D. Pati, N.S. Pillai, and D. B. Dunson. Journal of the American Statistical Association (2014)

  1. Posterior contraction in sparse Bayesian factor models for massive covariance matrices

D. Pati, A. Bhattacharya, N.S. Pillai, and D. B. Dunson. The Annals of Statistics (2014)

  1. Sparse Bayesian infinite factor models

A. Bhattacharya and D. B. Dunson. Biometrika (2011)


Scalable MCMC for shrinkage priors

1. MCMC for global-local shrinkage priors in high-dimensional settings

A. Bhattacharya and J. E. Johndrow. Handbook of Bayesian Variable Selection (2022). Marina Vannucci and Mahlet Tadesse Eds.

2. Sampling local scale parameters in high dimensional regression models

A. Bhattacharya and J. E. Johndrow. Handbook of Computational Statistics and Data Science (2021). Thomas Lee Eds.

3. Coupled Markov chain Monte Carlo for high-dimensional regression with Half-t priors

N. Biswas, A. Bhattacharya, P.E. Jacob, and J.E. Johndrow. The Journal of the Royal Statistical Society (Series B) (Accepted for publication)

4. Scalable Approximate MCMC Algorithms for the Horseshoe Prior

J. E. Johndow, P. Orenstein, and A. Bhattacharya. Journal of Machine Learning Research (2020)

5. Fast sampling with Gaussian scale-mixture priors in high-dimensional regression

A. Bhattacharya, A. Chakraborty, and B.K. Mallick. Biometrika (2016).

Statistical theory for variational inference

  1. Statistical optimality and stability of tangent transform algorithms in logit models

I. Ghosh, A. Bhattacharya, and D. Pati. Under revision.

  1. Structured Variational Inference in Bayesian State-Space Models

H. Wang, Y. Yang, D. Pati, and A. Bhattacharya. AISTATS 2022 (forthcoming)

  1. Statistical Guarantees and Algorithmic Convergence Issues of Variational Boosting

B.S. Guha, A. Bhattacharya, and D. Pati. ICTAI 2021

  1. Statistical Guarantees for Transformation Based Models with applications to Implicit Variational Inference

S. Plummer, S. Zhou, D. Pati, A. Bhattacharya, and D.B. Dunson. AISTATS 2021

  1. alpha-variational Bayes with statistical guarantees

Y, Yang, D. Pati, and A. Bhattacharya. The Annals of Statistics (2020)

  1. Bayesian fractional posteriors

A. Bhattacharya, D. Pati. and Y. Yang. The Annals of Statistics (2019)

  1. Statistical properties of Variational Bayes

D. Pati, A. Bhattacharya, and Y. Yang. AISTATS 2018

Bayesian model selection

  1. Approximate Laplace approximations for scalable model selection

D. Rossell, O. Abril, and A. Bhattacharya. The Journal of the Royal Statistical Society (Series B) (2021)

  1. A Hybrid Approximation to the Marginal Likelihood

E. Chuu, D. Pati, and A. Bhattacharya. AISTATS 2021.

  1. Probabilistic community detection with unknown number of communities

J. Geng, A. Bhattacharya, and D. Pati. Journal of the American Statistical Association (2019)

  1. Scalable Bayesian Variable Selection Using Nonlocal Prior Densities in Ultrahigh-Dimensional Settings

M. Shin, A. Bhattacharya, and V. E. Johnson. Statistica Sinica (2018)

Gaussian process priors

  1. Frequentist coverage and sup-norm convergence rate in Gaussian process regression

Y. Yang, A. Bhattacharya, and D. Pati. Under revision

  1. Optimal Bayesian estimation in random covariate design with a rescaled Gaussian process prior

D. Pati, A. Bhattacharya, and G. Cheng. JMLR (2015)

  1. Anisotropic function estimation using multi-bandwidth Gaussian processes

A. Bhattacharya, D. Pati, and D.B. Dunson. The Annals of Statistics (2014)