People@StatML

My research interests lie in the fields of machine learning and Bayesian statistics. Specifically, I develop new methods and models to discover latent structure in data, including cluster structure, using Bayesian nonparametrics, hierarchical Bayes, techniques for Bayesian model comparison, and other Bayesian statistical methods.

  kheller@stat.duke.eduMail   Twitter  

I am interested in neural coding and computation, Bayesian behavioral modeling, and statistical analysis of neural data.

I am a second year PhD Student in the Department of Statistical Sciences. My research interests are in Machine Learning. Previously I have done research on stochastic differential equations.

I'm a second-year PhD Student (since 2013) in the Computational Biology and Bioinformatics program at Duke University. Now my research emphasis is particularly placed on machine learning applications in genetics, genomics and other biologcial areas. My past research was margin theory, active Learning, deep Learning and data privacy based algorithm design.

I develop new Bayesian statistical models and apply them to solve problems in medicine, healthcare, and biology. I am also interested in Bayesian nonparametrics and scalable Bayesian inference.

On the theory side, I am interested in Bayesian nonparameterics, scalable Bayesian inference and stochastic processes. For applications, I attempt to understand the patterns of human behaviors with machine learning models. I am also curious about the connection between ML and statistical physics.

I am interested in how the neural and behavioral variance that we observe in the lab relates to outcomes in natural environments. My current work is on the genetics and social behavior of free-ranging rhesus macaques, focusing on quantifying social phenotypes using tools from ML and understanding how genetic variance in neural pathways contributes to those phenotypes.

My research focuses on applying methods from machine learning to brain data, in which capacity I collaborate with faculty in the Duke Statistical Machine Learning Group and the Information Initiative at Duke. I'm particulary interested in neuronal recording and functional imaging data, as well as eye tracking and choice modeling.

My research interests include estimation and model selection under both "large p, small n" and "large n, small p" settings as well as their applications in machine learning, change point detection, network analysis and recommender system. I'm currently working with Prof. David B. Dunson developing fast Bayesian methods for huge data sets, and with Prof. Chenlei Leng developing novel algorithms for variable screening and binary graph clustering.

I am a second year PhD Student in the Department of Statistical Science. My research interest lie in Bayesian machine learning, specifically in finding underlying structure in data. My current project focus on developing clustering methodology and transfer learning techniques for healthcare data.