Dr. Jiayu Zhou
Samsung Research America
Time: Thursday, Jan 22, 2015 (10am)
Location: EB 3105
In many fields one needs to build predictive models for a set of related machine learning tasks. Traditionally these tasks are treated independently and the inference is done separately for each task, which ignores inherent connections among the tasks. Multi-task learning aims to improve the generalization performance by building models for all tasks simultaneously, leveraging inherent relatedness of these tasks. In this talk, we show how multi-task learning can be applied to improve the predictive modeling from electronic medical records (EMR). We consider a novel data-driven framework for densifying EMR to address the challenges from the data sparsity when EMR are used for predictive modeling. By treating the densification of each patient as a learning task, the proposed multi-task learning algorithm simultaneously densifies all patients. As such, the densification of one patient leverages useful information from other patients. Experiments on real clinical data show that the densification can significantly improve the predictive performance.
Biography:Jiayu Zhou is a senior research scientist at Samsung Research America, leading the architecture design and development of a large-scale recommendation engine, delivering personalized Ads/TV programs recommendation to millions Samsung Smart TV devices. Jiayu received his Ph.D. degree in computer science at Arizona State University in 2014, under the supervision of Professor Jieping Ye. Jiayu has a broad research interest in large-scale machine learning and data mining, and biomedical informatics. He has served as Senior Program Committee of IJCAI 2015. He also served as program committee members in premier conferences such as NIPS, ICDM, SDM, WSDM, ACML and PAKDD. Jiayu currently serves as an Associate Editor of Neurocomputing. Most of Jiayu's research has been published in top machine learning and data mining venues including NIPS, SIGKDD, ICDM and SDM. One of his papers has been selected for the best student paper award in ICDM 2014.
Dr. Pang-Ning Tan