Hantian Zhang

I am a first year Ph.D student advised by Ce Zhang at ETH Zurich. My research focus on speeding up machine learning systems and making them more accessible to users.

News

• Jun.26th, 2017: Our work "Scalable Inference of Decision Tree Ensembles: Flexible Design for CPU-FPGA Platforms" is accepted at FPL 2017.
• May.12th, 2017: Our ZipML work "The ZipML Framework for Training Models with End-to-End Low Precision: The Cans, the Cannots, and a Little Bit of Deep Learning" is accepted at ICML 2017.
• May.10th, 2017: I gave a talk "Faster Machine Learning via Low-Precision Communication and Computation" with Dan Alistarh at Nvidia GPU Technology Conference (GTC) 2017. (Video, Slides)

Publications

Scalable Inference of Decision Tree Ensembles: Flexible Design for CPU-FPGA Platforms
Muhsen Owaida, Hantian Zhang, Ce Zhang, Gustavo Alonso
FPL 2017 (To Appear)

The ZipML Framework for Training Models with End-to-End Low Precision: The Cans, the Cannots, and a Little Bit of Deep Learning.
Hantian Zhang, Jerry Li, Kaan Kara, Dan Alistarh, Ji Liu, Ce Zhang
ICML 2017 (To Appear)

Generative adversarial networks recover features in astrophysical images of galaxies beyond the deconvolution limit.
Ce Zhang, Kevin Schawinski, Hantian Zhang, Lucas Fowler, Gokula Krishnan Santhanam
MNRAS 2017

Education

• Ph.D. Candidate, ETH Zurich, 2017.5 - Present
• M.S., ETH Zurich, 2014.9 - 2017.4
• B.S., Peking University, 2010.9 - 2014.6