Geng Ji Publications


Ph.D. Candidate
Department of Computer Science
University of California, Irvine

4241 Donald Bren Hall
Irvine, CA 92697
gji1 [at] uci [dot] edu

Geng Ji (季耿)

I am a PhD candidate in the Computer Science Department of University of California, Irvine, advised by Prof. Erik Sudderth. My research interests are broadly in probabilistic machine learning, such as probabilistic graphical models, large-scale variational inference, Bayesian nonparametric statistics, and their applications in computer vision and natural language processing.

I did summer internships at Facebook AI and Disney Research, mentored by Dr. Huazhong Ning and Stephan Mandt. I got Master's degrees in CS from Brown University and UC Irvine, and finished my undergrad in engineering physics at Tsinghua University, China.


Geng Ji, Dehua Cheng, Huazhong Ning, Changhe Yuan, Hanning Zhou, Liang Xiong, and Erik B. Sudderth. Variational Training for Large-Scale Noisy-OR Bayesian Networks. Uncertainty in Artificial Intelligence (UAI), 2019. [pdf][supplement][poster]

Geng Ji, Robert Bamler, Erik B. Sudderth, and Stephan Mandt. Bayesian Paragraph Vectors. Advances in Approximate Bayesian Inference Workshop at NeurIPS, 2017. [pdf][poster]

Geng Ji, Michael C. Hughes, and Erik B. Sudderth. From Patches to Images: A Nonparametric Generative Model. International Conference on Machine Learning (ICML), 2017. [pdf][supplement][poster][code]

Geng Ji, Michael C. Hughes, and Erik B. Sudderth. From Patches to Images via Hierarchical Dirichlet Process. Practical Bayesian Nonparametrics Workshop at NeurIPS, 2016. [pdf]


UC Irvine CS 274B: Learning in Graphical Models.

UC Irvine CS 177: Aplications of Probability in Computer Science.

Brown CSCI 1420: Introduction to Machine Learning.

Conference Review