I am a postdoctoral researcher at Microsoft Research New England. My research interests are in probabilistic methods for machine learning. I have worked on topics including approximate inference, Gaussian processes, kernel/spectral methods, generative models, and Bayesian neural networks.

I obtained my Ph.D. in Computer Science (2015-2020) from Tsinghua University, advised by Jun Zhu. Last year I spent the summer at DeepMind, London as a research scientist intern and the rest of the year visiting Vector Institute. I have also spent a summer interning at RIKEN-AIP, Tokyo. I received my B.E. from the Department of Computer Science and Technology at Tsinghua University.

Github Twitter

Research Highlights

MORE

Nonparametric Score Estimators

Yuhao Zhou, Jiaxin Shi, and Jun Zhu.

ICML, 2020. [pdf] [arxiv] [code]

Sparse Orthogonal Variational Inference for Gaussian Processes

Jiaxin Shi, Michalis K. Titsias, and Andriy Mnih.

AISTATS, 2020. [pdf] [arxiv]

Best Student Paper Runner-Up at AABI 2019.

A Spectral Approach to Gradient Estimation for Implicit Distributions

Jiaxin Shi, Shengyang Sun, and Jun Zhu.

ICML, 2018. [pdf] [arxiv] [code]

Scalable Training of Inference Networks for Gaussian-Process Models

Jiaxin Shi, Mohammad Emtiyaz Khan, and Jun Zhu.

ICML, 2019. [pdf] [arxiv] [code]

Software

During my PhD I led the development of ZhuSuan [github] [doc] [arxiv], an open-source probabilistic programming project based on Tensorflow.

Curriculum Vitae

My CV can be downloaded from this link: [pdf]