Shaobo Han

Postdoctoral Associate

Department of Statistical Science

Duke University

Biography

I am currently a Postdoctoral Associate at Duke Department of Statistical Science, working with David Dunson. My research interest lies in the intersection of Machine Learning, Statistics and Signal Processing, with particular focus on probabilistic modeling and inference for high dimensional, complex, and intricately structured data. My Ph.D. advisor was Lawrence Carin.

Interests

Probabilistic Methods
Tensor Decompositions
Variational Inference
Network Science
Multiscale Modeling

Education

Ph.D. in Machine Learning, 2016

Duke University
M.S. in Statistical Science, 2016

Duke University
M.S. in Signal Processing, 2010

Chinese Academy of Sciences
B.S. in Electrical Engineering, 2007

Xidian University

Selected Publications

Shaobo Han, David B. Dunson. Multiresolution Tensor Decomposition for Multiple Spatial Passing Networks. In ArXiv, 2018.

Preprint

Yunchen Pu, Zhe Gan, Ricardo Henao, Chunyuan Li, Shaobo Han, Lawrence Carin. VAE Learning via Stein Variational Gradient Descent. In NIPS, 2017.

Preprint PDF

Shaobo Han, Xuejun Liao, David B. Dunson, Lawrence Carin. Variational Gaussian Copula Inference. In AISTATS, 2016.

Preprint PDF Code Poster

Yan Kaganovsky, Shaobo Han, Soysal Degirmenci, David G. Politte, David J. Brady, Joseph A. O’Sullivan, Lawrence Carin. Alternating Minimization Algorithm with Automatic Relevance Determination for Transmission Tomography under Poisson Noise. In SIIMS, 2015.

Preprint PDF Code

Shaobo Han, Lin Du, Esther Salazar, Lawrence Carin. Dynamic Rank Factor Model for Text Streams. In NIPS, 2014.

Preprint PDF Poster

Xin Yuan, Vinayak Rao, Shaobo Han, Lawrence Carin. Hierarchical Infinite Divisibility for Multiscale Shrinkage. In IEEE-TSP, 2014.

PDF

Shaobo Han, Xuejun Liao, Lawrence Carin. Integrated Non-Factorized Variational Inference. In NIPS, 2013.

PDF Poster Slides

Shaobo Han, Xuejun Liao, Lawrence Carin. Cross-Domain Multitask Learning with Latent Probit Models. In ICML, 2012.

Preprint PDF Poster

Teaching and Mentoring

Instructor, STA 111: Probability and Statistical Inference (Duke STA 111), Summer 2018
Data+ Mentor, Predicting Pancreatic Cancer from the EMR Data, May - July 2016
Teaching Assistant, Random Signal and Noise (Duke ECE 581), Fall 2012 and Fall 2013

I received the Charles Rowe Vail Memorial Outstanding Graduate Teaching Award from Duke University in 2013 - 2014

Professional Activities

Reviewer

Journal of the American Statistical Association (JASA)
The Canadian Journal of Statistics (CJS)
IEEE Transactions on Signal Processing (TSP)
IEEE Transactions on Image Processing (TIP)
IEEE Transactions on Knowledge and Data Engineering (TKDE)
SIAM Journal on Imaging Sciences (SIIMS)
Statistics and Computing (Springer)
Journal of Artificial Intelligence Research (JAIR)

Program Committee Member

Neural Information Processing Systems (NIPS)
International Conference on Machine Learning (ICML)
International Conference on Learning Representations (ICLR)
International Conference on Artificial Intelligence and Statistics (AISTATS)
International Joint Conference on Artificial Intelligence (IJCAI)
AAAI Conference on Artificial Intelligence (AAAI)
Asian Conference on Machine Learning (ACML)

VIP Consultant

The American Statistical Association (ASA) DataFest, 2016; 2017; 2018

Contact

shaobohan@gmail.com
206B Old Chemistry, Box 90251, Durham, NC 27708, USA