Yanbo's CV

Education

• Ph.D in Machine Learning, Georgia Institute of Technology, 2017 Spring - Present
• Ph.D in Computer Science (Transfered), Johns Hopkins University, 2015 - 2016
• Ph.D in Language Technologies (LOA), Carnegie Mellon University, 2010 - 2013
• M.S. in Applied Math and Statistics, University of Minnesota, 2010
• M.S. & B.S. in Computer Science, Harbin Institute of Technology, 2006

Work experience

• 2014 - 2015: Visiting Scholar at University of California Berkeley

  Scale student modeling to Massive Open Online Courses (MOOC) – edX.

• 2006 - 2008: Software Engineer at Lenovo Group Ltd, China

  Develop information integration system for CCB bank using C/C++.

Awards and Honors

• 2018: Google Summer of Code (GSoC) developer

  R project for statistical computing

• 2012: Best Student Paper Award

  The 5th International Conference on Educational Data Mining (EDM)

• 2010: Outstanding Graduates

  Department of Mathematics and Statistics, University of Minnesota Duluth

• 2010 Summer: Data Sciences Summer Institute (DSSI) Fellowship

  University of Illinois Urbana Champaign Summer School

• 2009 Summer: NAACL Scholarship Award

  Johns Hopkins HLT Summer School

Skills

• Programming language: C/C++, Python, Pytorch, R, and Perl
• Other tools: Matlab, SQL, BUGs/STAN

Selected Publications

Full publications can be found here.

UnfoldML: Cost-Aware and Uncertainty-Based Dynamic 2D Prediction for Multi-Stage Classification

Xu, Y.*, Khare, A.*, Matlin, G., Ramadoss, M., Kamaleswaran R., Zhang, C., Tumanov, A., 2022, December. UnfoldML: Cost-Aware and Uncertainty-Based Dynamic 2D Prediction for Multi-Stage Classification. Advances in Neural Information Processing Systems. *Equal contribution

Split-Treatments Analysis to Rank Heterogenous Causal Effects for Novel Treatments

Xu, Y., Mahajan, D., Manrao, L., Sharma, A., & Kiciman, E., 2021, March. Split-Treatments Analysis to Rank Heterogenous Causal Effects for Novel Treatments. In Proceedings of the International Conference on Web Search and Data Mining

HOLMES: Health OnLine Model Ensemble Serving for Deep Learning Models in Intensive Care Units

Hong, S.*, Xu, Y.*, Khare, A.*, Priambada, S.*, Maher, K., Aljiffry, A., Sun, J., Tumanov, A., 2020, August. HOLMES: Health OnLine Model Ensemble Serving for Deep Learning Models in Intensive Care Units. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. ACM. *Equal contribution

RAIM: Recurrent Attentive and Intensive Modeling of Multimodal Continuous Patient Monitoring Data

Xu, Y., Biswal, S., Deshpande, S.R., Maher, K.O. and Sun, J., 2018, July. RAIM: Recurrent Attentive and Intensive Model of Multimodal Patient Monitoring Data. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (pp. 2565-2573). ACM.

Predicting Changes in Pediatric Medical Complexity using Large Longitudinal Health Records

Xu, Y., Bahadori, M.T., Searles, E., Thompson, M., Javier, T.S. and Sun, J., 2017. Predicting Changes in Pediatric Medical Complexity using Large Longitudinal Health Records. In AMIA Annual Symposium Proceedings (Vol. 2017, p. 1838). American Medical Informatics Association.

A Non-parametric Bayesian Approach for Estimating Treatment-Response Curves from Sparse Time Series

Xu, Y., Xu, Y. and Saria, S., 2016, December. A Bayesian nonparametric approach for estimating individualized treatment-response curves. In Machine Learning for Healthcare Conference (pp. 282-300).

Comparison of methods to trace multiple subskills: Is LR-DBN best?

Xu, Y. and Mostow, J., 2012. Comparison of Methods to Trace Multiple Subskills: Is LR-DBN Best?. International Educational Data Mining Society.