Research

Data Science enables discovery and innovation in a wide range of knowledge domains in the sciences and beyond.

Keaton Hamm

Assistant Professor, Department of Mathematics

Structure in Data: I seek to understand and utilize low-dimensional structures in high-dimensional data. Exploiting these structures allows us to find faster algorithms for many data science tasks such as classification or regression, and sometimes mitigate the curse of dimensionality. 

 

Ren-cang Li

Professor, Department of Mathematics

Li Wang

Associate Professor, Department of Mathematics

Mathematical Data Science and Real Applications: We concentrate on developing advanced machine learning models and algorithms, including probabilistic graph learning, latent data representation, multimodality data analysis and dimensionality reductions. We also apply the proposed models and algorithms on real medical imaging data and single-cell data.  

 

Pedro Maia

Assistant Professor, Department of Mathematics

Research interests: My research interests include applying data-driven methods, machine learning, and traditional applied mathematics expertise to a variety of problems in computational neuroscience, neurology, and other biological/medical scenarios.

 

Suvra Pal

Associate Professor, Department of Mathematics

Optimal Treatment Strategy: Developing next-generation machine learning-based biostatistical models and computationally efficient methods in high-dimensional settings to accurately predict disease cure and provide guidance for treatment allocation.

 

Shan Sun-Mitchell

Professor, Department of Mathematics

Research interests: Statistical theory, nonparametric statistical inference, and their practical application in data-driven methodologies related to health.

 

Xinlei Wang

Professor, Department of Mathematics

Statistical omics: Developing advanced statistical methods and computational techniques for analysis of high-dimensional, large-scale biological data, such as genomics, epigenomics, transcriptomics, proteomics, and metabolomics, to unravel complex biological processes and facilitate the discovery of genetic markers relevant to diagnosis and prognosis.

 

Bayesian deep learning:  Combining Bayesian statistical methods with deep learning models, integrating uncertainty estimation into neural networks to enhance robustness, generalization, and interpretability in various applications.

Explainable Artificial Intelligence (XAI): Developing interpretable and transparent models, algorithms, and techniques in artificial intelligence to enhance the understanding of machine learning systems' decisions, making them more accountable and trustworthy.

Integrative and meta-analytical methods in biomedical studies: Developing statistical and computational techniques to synthesize and analyze data from multiple sources, studies, or datasets, aiming to derive comprehensive insights, identify patterns, and draw robust conclusions that contribute to a more holistic understanding of complex biological phenomena and disease processes.