Welcome, I am currently a first year Machine Learning PhD student at Caltech.

Education Background

09/2018 -
PhD in Computer Science, California Institute of Technology

09/2014 - 07/2018
B.S. in Computer Science, Kuang Yaming Honors School, Nanjing University
(Selected 91 from 3400 in total,exempted from Natinoal College Entrance Examination)

08/2016 - 01/2017
Exchange student, Computer Science department, Duke University (Selected 11 from 91)
GPA: 4.0/4.0
Courses: Machine Learning(Graduate Level)(A+), Intro High Dim Data Analysis(A+), Undergraduate Research(A), Statistics(A+)

Research Experience

08/2016 - 09/2017
Research Assistant, Advisor: Prof. Lawrence Carin, Duke University

03/2017 - 09/2017
Research Assistant, Advisor: Prof. Cynthia Rudin, Duke University

09/2015 - 06/2018
Research Assistant, Advisor: Prof. Yu-Feng Li, LAMDA group, Nanjign University


News

• One paper accepted by AISTATS 2019
• One paper accepted by AAAI 2018
• Two papers accepted by NIPS 2017

Presentations

Bidirectinal GAN



Recent Highlights

On Connecting Stochastic Gradient MCMC and Differential Privacy
Bai Li, Changyou Chen, Hao Liu and Lawrence Carin.
In Preceedings of International Conference on Artificial Intelligence and Statistics(AISTATS), 2019.
Abstract
Deep Learning for Case-based Reasoning through Prototypes:A Neural Network that Explains its Predictions
Oscar Li*, Hao Liu*, Chaofan Chen and Cynthia Rudin (* equal contribution).
In Preceedings of AAAI Conference on Artificial Intelligence(AAAI), 2018.
Abstract
ALICE:Towards Understanding Adversarial Learning for Joint Distribution Matching [Poster at NIPS 2017]
Chunyuan Li, Hao Liu, Changyou Chen, Yunchen Pu, Liqun Chen, Ricardo Henao and Lawrence Carin.
In Preceedings of Neural Information Processing Systems(NIPS), 2017.
Abstract Code
Triangle Generative Adversarial Networks [Poster at NIPS 2017]
Zhe Gan, Liqun Chen, Weiyao Wang, Yunchen Pu, Yizhe Zhang, Hao Liu, Chunyuan Li and Lawrence Carin.
In Preceedings of Neural Information Processing Systems(NIPS), 2017.
Abstract Code