Home Page Image
 
 
 

 
Welcome to My Homepage

I completed my PhD majoring in Electrical Engineering in June, 2016. I was a member of MELODI (MachinE Learning for Optimization and Data Interpretation) lab. My work was under the supervision of Professor Jeff Bilmes. My research interests include:

  1. Machine learning,
  2. Combinatorial optimization,
  3. Speech processing and speech recognition.

Educational Background
  1. Ph.D. in Electrical Engineering, University of Washington, Fall 2013-Spring 2016.
  2. M.S. in Electrical Engineering, University of Washington, Fall 2011-Fall 2013.
  3. B.S. in Electronic Information, Huazhong University of Science and Technology, June 2011.


Internships
  1. Research Intern, Siri, Apple, Cupertino CA. June 2014-Sept 2014
  2. Research Intern, Broadcom, Irvine CA. June 2012-Sept 2012
  3. Summer intern, China Mobile Group, Guangdong China, July 2010-August 2010.


TA Experiences
  1. Spring 2016: EE596 Submodular Function Optimization and Applications to Machine Learning
  2. Spring 2012: EE215 Fundamentals of Electring Engineering
  3. Winter 2012: PMP EE518 Discrete-time Signal Processing


Professional Activities
  1. Reviewer: NIPS 2016, ICML 2016, AAAI 2016, NIPS 2015, ICML 2015, NIPS 2014, JMLR


Thesis
  1. Submodular Optimization and Data Processing, Ph.D. dissertation, University of Washington, June 2016. [PDF]
Conference Papers
  1. Wenruo Bai, Rishabh Iyer, Kai Wei, and Jeff Bilmes. Algorithms for Optimizing the Ratio of Submodular Functions, In ICML, New York, USA, June 2016. [paper]
  2. Kai Wei, Rishabh Iyer, Shengjie Wang, Wenruo Bai, and Jeff Bilmes. Mixed Robust/Average Submodular Partitioning: Fast Algorithms, Guarantees, and Applications, In Neural Information Processing Systems (NIPS 2015), Montreal, Canada, December 2015. [short version] [extended version]
  3. Kai Wei, Rishabh Iyer, and Jeff Bilmes. Submodularity in Data Subset Selection and Active Learning, In Intl. Conf. on Machine Learning (ICML 2015), Lille, France, July 2015. [short version] [extended version] [poster] [slides] [talk]
  4. Kai Wei, Rishabh Iyer, and Jeff Bilmes. Fast Multi-stage Submodular Maximization, In Intl. Conf. on Machine Learning (ICML 2014), Beijing, China, June 2014. Recommended for JMLR Fast Track Review, 18 out of 1260+ [short version] [extended version] [poster] [slides] [talk]
  5. Kai Wei, Yuzong Liu, Katrin Kirchhoff, Chris Bartel, and Jeff Bilmes. Submodular Subset Selection for Large-Scale Speech Training Data, In Proc. IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (ICASSP 2014), Florence, Italy, May 2014. [paper] [poster]
  6. Kai Wei, Yuzong Liu, Katrin Kirchhoff, and Jeff Bilmes. Unsupervised Submodular Subset Selection for Speech Data , In Proc. IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (ICASSP 2014), Florence, Italy, May 2014. [paper] [poster]
  7. Kai Wei*, Yuzong Liu*, Katrin Kirchhoff, and Jeff Bilmes. Using Document Summarization Techniques for Speech Data Subset Selection , In North American chapter of the Association for Computational Linguistics/Human Language Technology Conference (NAACL/HLT-2013), Atlanta, GA, June 2013. (* equal contribution) [paper] [slides] [talk]
  8. Yuzong Liu, Kai Wei, Katrin Kirchhoff, Yisong Song, and Jeff Bilmes. Submodular Feature Selection For High-Dimensional Acoustic Score Spaces . In Proc. IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (ICASSP 2013) , Vancouver, Canada, 2013. [paper] [poster]
Workshop Papers and Preprints
  • Kai Wei*, Max Libbrecht*, Jeff Bilmes, and William Noble. Choosing panels of genomics assays using submodular optimization, 2016. [preprint]
  • Kai Wei, Rishabh Iyer, Shengjie Wang, Wenruo Bai, and Jeff Bilmes. Mixed Robust/Average Submodular Partitioning, In Optimization for Machine Learning Workshop 2015, Montreal, Canada, December 2015. [paper]
  • Kai Wei, Rishabh Iyer, Shengjie Wang, Wenruo Bai, and Jeff Bilmes. How to Intelligently Distribute Training Data to Multiple Compute Nodes: Distributed Machine Learning via Submodular Partitioning, In Workshop on Machine Learning Systems (LearningSys) 2015, Montreal, Canada, December 2015. [paper]


Contact Information
  1. Email: kaiwei at uw dot edu