Abstract: In many biomedical prediction scenarios, it is difficult to identify the ideal predictor due to incompleteness of knowledge and/or data quality issues. In such scenarios, a powerful approach is to learn heterogeneous ensemble predictors that are learnt from a large and diverse set of base predictors. This talk will describe the basics of these predictors as well as novel algorithms for learning such predictors from large biomedical datasets. Preliminary results from an innovative application of these predictors to DREAM Challenges will also be presented.

Speaker Bio: Gaurav Pandey is an Assistant Professor in the Department of Genetics and Genomic Sciences at the Icahn School of Medicine Mount Sinai (New York) and is part of the Icahn Institute for Genomics and Multiscale Biology. He completed his Ph.D. in computer science and engineering from the University of Minnesota, Twin Cities in 2010, and subsequently completed a post-doctoral fellowship at the University of California, Berkeley. His primary fields of interest are computational biology, genomics and large-scale data analysis and mining, and he has published extensively in these areas. He received the IBM Faculty Award in 2015.