CV
About Me

I’m Wei Wen, a Ph.D. candidate in Duke University, supervised by Dr. Hai Helen Li and Dr. Yiran Chen. My research is Machine Learning and its applications in Computer Vision and Natural Language Processing. Recently, I focus on structural learning for efficient deep learning on the edge, optimization algorithms for distributed machine learning, and learning algorithm understanding.

More specific, I am studying learning algorithms to escape sharp minima in deep neural networks to understand the generalization, TernGrad SGD to overcome the communication bottleneck in distributed machine learning, and structural leaning algorithms to learn sparse and low-rank structures in deep neural networks for faster inference.

My Ph.D. thesis is “Efficient and Scalable Deep Learning”. Dissertation committee: Hai Helen Li, Yiran Chen, Robert Calderbank, Yangqing Jia and Guillermo Sapiro.

I had internship in Facebook Research, Microsoft Research Redmond & Asia and HP Labs, where I incorporated my research into industrial AI productions.

GitHub, Google Scholar

Industrial Experience

More in LinkedIn.

Facebook Research – AI Infra & Applied Machine Learning, Menlo Park, CA, USA, 05/2018-08/2018

Research Intern, Mentor: Yangqing Jia
– Caffe2 and Personalization
– Distributed Machine Learning

Microsoft Research – Web Search and AI, Redmond & Bellevue, WA, USA, 05/2017-07/2017

Research Intern, Mentors: Yuxiong He & Fang Liu
– Machine Reading Comprehension
– Recurrent Neural Nets

HP Labs – Platform Architecture Group, Palo Alto, CA, USA, 05/31/2016-08/31/2016

Research Intern, Mentor: Cong Xu. Manager: Paolo Faraboschi
– Worked on distributed deep learning.

Agricultural Bank of China – Software Development Center, Beijing, 07/2013-07/2014

Software Engineer
– Developed web services for online bank transactions.

Microsoft Research – Mobile and Sensing Systems Group, Beijing, China, 04/2013-06/2013

Research Intern
– Worked on mobile computer vision

Tencent Inc. – Advertising Platform and Products Division, Beijing, China, 07/2012-09/2012

Software Engineer Intern.

 

Publications

  • Wei Wen, Yandan Wang, Feng Yan, Cong Xu, Yiran Chen, Hai Li,  “SmoothOut: Smoothing Out Sharp Minima to Improve Generalization in Deep Learning”, preprint. [paper][code]
  • Wei Wen, Yuxiong He, Samyam Rajbhandari, Minjia Zhang, Wenhan Wang, Fang Liu, Bin Hu, Yiran Chen, Hai Li,  “Learning Intrinsic Sparse Structures within Long Short-Term Memory”,the 6th International Conference on Learning Representations (ICLR), 2018. [poster][paper][code]
  • Wei Wen, Cong Xu, Feng Yan, Chunpeng Wu, Yandan Wang, Yiran Chen, Hai Li,  “TernGrad: Ternary Gradients to Reduce Communication in Distributed Deep Learning”,the 31st Annual Conference on Neural Information Processing Systems (NIPS), 2017. (Oral, 40/3240=1.2%. Available in PyTorch/Caffe2.). [paper][video][slides][code][poster]
  • Wei Wen, Cong Xu, Chunpeng Wu, Yandan Wang, Yiran Chen, Hai Li,  “Coordinating Filters for Faster Deep Neural Networks”, Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017. [paper][code][poster]
  • Wei Wen, Chunpeng Wu, Yandan Wang, Yiran Chen, Hai Li,  “Learning Structured Sparsity in Deep Neural Networks”, the 30th Annual Conference on Neural Information Processing Systems (NIPS), 2016. Acceptance Rate: 568/2500=22.7%. (Integrated into Intel Nervada) [paper][code][poster]
  • Jongsoo Park, Sheng Li, Wei Wen, Ping Tak Peter Tang, Hai Li, Yiran Chen, Pradeep Dubey,  “Faster CNNs with Direct Sparse Convolutions and Guided Pruning”, the 5th International Conference on Learning Representations (ICLR), 2017. [paper][code][media]
  • Chunpeng Wu, Wei Wen, Tariq  Afzal, Yongmei  Zhang, Yiran Chen, Hai Li,  “A Compact DNN: Approaching GoogLeNet-Level Accuracy of Classification and Domain Adaptation”, CVPR, 2017. [paper]
  • Yandan Wang, Wei Wen, Linghao Song, Hai Li, “Classification Accuracy Improvement for Neuromorphic Computing Systems with One-level Precision Synapses “, ASP-DAC, 2017. (Best Paper Award). [paper]
  • Wei Wen, Chunpeng Wu, Yandan Wang, Kent Nixon, Qing Wu, Mark Barnell, Hai Li, Yiran Chen, “A New Learning Method for Inference Accuracy, Core Occupation, and Performance Co-optimization on TrueNorth Chip”, 53rd ACM/EDAC/IEEE Design Automation Conference (DAC), 2016. Acceptance Rate: 152/876=17.4%. (Best Paper Nomination, 16/876=1.83%). [paper]
  • Wei Wen, Chi-Ruo Wu, Xiaofang Hu, Beiye Liu, Tsung-Yi Ho, Xin Li, Yiran Chen, “An EDA Framework for Large Scale Hybrid Neuromorphic Computing Systems”, 52nd ACM/EDAC/IEEE Design Automation Conference (DAC), 2015. Acceptance Rate: 162/789=20.5%. (Best Paper Nomination, 7/789=0.89%). [paper]
  • Yandan Wang, Wei Wen, Beiye Liu, Donald Chiarulli, Hai Li, “Group Scissor: Scaling Neuromorphic Computing Design to Big Neural Networks”, 54th ACM/EDAC/IEEE Design Automation Conference (DAC), 2017. Acceptance Rate: 24%. [paper]
  • Jongsoo Park, Sheng R. Li, Wei Wen, Hai Li, Yiran Chen, Pradeep Dubey,  “Holistic SparseCNN: Forging the Trident of Accuracy, Speed, and Size”, arXiv 1608.01409, 2016. (in Intel Developer Forum 2016, pages 41-43). [paper][code]

Talks and Presentations

Activities

  • Serving as a reviewer of NIPS, ICLR, TNNLS, TCAD, Neurocomputing, ICME, etc
  • Activity volunteer, Machine Learning for Girls, FEMMES (Female Excelling More in Math, Engineering, and Science) Capstone at Duke University, 02/2018
  • Conference volunteer, ESWEEK 2016, OCTOBER 2-7, PITTSBURGH, PA, USA, 10/2016

Education

08/2017-12/2019 (Estimated)
Ph.D. in Electrical and Computer Engineering, Duke University, Durham, NC, United States

09/2014-08/2017 (Transferred to Duke University)
Ph.D. in Electrical and Computer Engineering, University of Pittsburgh, Pittsburgh, PA, United States

09/2010-01/2013
Master in Electronic and Information Engineering, Beihang University, Beijing, China

09/2006-07/2010
Bachelor in Electronic and Information Engineering, Beihang University, Beijing, China