Hsin-Pai (Dave) Cheng

Ph.D. Student

News

11/2018 - Our work on decentralized privacy preserving is accepted by NIPS'18 PPML Workshop!
11/2018 - Our work on Compress Deep Neural Network is accepted by NIPS'18 CDNNRIA Workshop as spotlight presentation!
10/2018 - Our latest work with DNN quantization is on arXiv!

Research Projects

My research is machine learning and its applications. I am focusing on efficient deep learning on the edge, optimization algorithms for distributed machine learning, machine learning privacy and security.

Competition

Low Power Image Recognition Challenge (LPIRC) at CVPR

In 2017, I won the special prize of track 3 at Low Power Image Recognition Challenge (LPIRC) @ CVPR2017.

In 2018, a direct a team of undergrads to participate LPIRC 2018 at CVPR and we won 3rd place of track 2.

Our team name is newwhitecheng (which is my github username). For more details please see the arXiv paper.

Duke Machine Learning 2018 Kaggle Competition

When taking the class, Probabilistic Machine Learning (STA561), I won the 1st place.

The score and leader board result is a available on Kaggle website .

Publication

2018

Workshop Differentiable Fine-grained Quantization for Deep Neural Network Compression

Hsin-Pai Cheng, Yuanjun Huang, Xuyang Guo, Yifei Huang, Feng Yan, Hai Li, Yiran Chen
NIPS 2018 Workshop on Compact Deep Neural Networks with Industrial Applications (CDNNRIA)

Workshop LEASGD: an Efficient and Privacy-Preserving Decentralized Algorithm for Distributed Learning

Hsin-Pai Cheng, Patrick Yu, Haojing Hu, Feng Yan, Shiyu Li, Hai Li and Yiran Chen
NIPS 2018 Workshop on Privacy Preserving Machine Learning (PPML)

ConferenceSpecial Session AdverQuil: an Efficient Adversarial Detection and Alleviation Technique for Black-Box Neuromorphic Computing Systems

Hsin-Pai Cheng, Juncheng Shen, Huanrui Yang, Qing Wu, Hai L, Yiran Chen
P24th Asia and South Pacific Design Automation Conference (ASPDAC)