My research develops semiparametric and nonparametric functional methods for analyzing highly correlated, high-dimensional data. I focus on nonparametric multitask learning, multilevel graphical network estimation and inference, multilevel kernel machine methods, and probabilistic machine learning frameworks to jointly address complex dependence structures, identify important features, and quantify uncertainty. I develop hybrid frequentist–Bayesian approaches to enhance model flexibility and inferential robustness.
My research areas are listed as
Probabilistic machine learning/ kernel machine learning/survival multilevel learning
Functional graphical model, network/causal discovery, and Markov Random Field
Functional variable selection for highly correlated variables
Nonparametric Bayesian method/computing
High-dimensional functional data analysis
Semiparametric mixed model/nonlinear mixed model/functional longitudinal data analysis
Measurement error in high-dimensional covariates
My application areas are listed as
Functional magnetic resonance imaging (fMRI) for cognitive neuroscience
Biomedical engineering (Biosensing, Photonics, Optics): Brain/Breast tumor cell line, real-time and streaming signal data
Biostatistics (Environmental Health, Epidemiology, Public Health, Survival-life Time, Equine Medicine, and Various Cancer Metastasis)
Bioinformatics (Functional Genomics, System Biology, Protein-Protein Interaction, Proteomics).