Adams Wei Yu

(Adams) Wei Yu

I am a research scientist at Google Brain. I graduated from SCS of CMU, with a PhD in Machine Learning and an MSc in Lanugage Technologies, advised by Jaime Carbonell and Alex Smola.

Email: adams(my last name)wei AT gmail DOT com

Recent News

Selected Awards

  • Snap PhD Fellow (12 selected worldwide), 2018.
  • CMU Presidential Fellow, 2017-2018.
  • NVIDIA PhD Fellowship (11 selected worldwide), 2017.
  • Invited young researcher (200 selected worldwide) in Math and CS to attend Heidelberg Laureate Forum, 2015.
  • Siebel Scholar (85 selected worldwide), class of 2015.
  • INFORMS data mining best student paper finalist, 2014.
  • CMU research fellowship, 2013-present.
  • ICME 2011 best paper award nomination, 2011.

Selected Industrial Internship

  • 2017.5 -- 2017.8, Research Intern, Google Brain. Mentor: Quoc Le and Kai Chen.
  • 2016.5 -- 2016.8, Research Intern, Google Brain and Web Answers. Mentor: Quoc Le and Hongrae Lee.
  • 2015.5 -- 2015.8, Research Intern, Machine Learning Group, Microsoft Research Redmond. Mentor: Lin Xiao.
  • 2012.8 -- 2012.11, Research Intern, DMAS Group, Microsoft Research Asia. Mentor: Haixun Wang.

Selected Publications

PhD Thesis:
  • "Effective and Efficient Learning at Scale".
    Adams Wei Yu.
    Committee: Jaime Carbonell, Alex Smola, Ruslan Salakhutdinov, Quoc Le (Google Brain), Chris Manning (Stanford).
  • "Normalized Gradient with Adaptive Stepsize Method for Deep Neural Network Training".
    Adams Wei Yu, Qihang Lin, Ruslan Salakhutdinov, Jaime Carbonell.
    Arxiv, Bibtex.

  • "Doubly Stochastic Primal-Dual Coordinate Method for Bilinear Saddle-Point Problem".
    Adams Wei Yu, Qihang Lin, Tianbao Yang.
    Arxiv, Bibtex.
Journal and Conference:
  • "DSCOVR: Randomized Primal-Dual Block Coordinate Algorithms for Asynchronous Distributed Optimization".
    Lin Xiao, Adams Wei Yu, Qihang Lin, Weizhu Chen.
    In JMLR. Arxiv.

  • "QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension".
    Adams Wei Yu, David Dohan, Thang Luong, Rui Zhao, Kai Chen, Mohammad Norouzi, Quoc Le.
    In ICLR 2018. Full Paper, Arxiv. Bibtex

  • "Orthogonal Weight Normalization: Solution to Optimization over Multiple Dependent Stiefel Manifolds in Deep Neural Networks". (Full Oral)
    Lei Huang, Xianglong Liu, Bo Lang, Adams Wei Yu, Bo Li.
    In AAAI 2018. Arxiv, Bibtex.

  • "On Computationally Tractable Selection of Experiments in Regression Models". (Accepted, to appear)
    Yining Wang, Adams Wei Yu, Aarti Singh.
    In JMLR. Arxiv, Bibtex.

  • "Learning to Skim Text". (Long Paper)
    Adams Wei Yu, Hongrae Lee, Quoc Le.
    In ACL 2017. Full paper, Arxiv, Bibtex.

  • "An Improved Gap-Dependency Analysis of the Noisy Power Method". (Full oral)
    Maria Florina Balcan**, Simon S. Du**, Yining Wang**, Adams Wei Yu**. (** α-β order)
    In COLT 2016. Full paper, Arxiv, Bibtex.

  • "Adadelay: Delay Adaptive Distributed Stochastic Optimization".
    Suvrit Sra, Adams Wei Yu, Mu Li, Alex Smola.
    In AISTATS 2016. Full paper, Arxiv, Bibtex.
  • "Efficient Structured Matrix Rank Minimization".
    Adams Wei Yu, Wanli Ma, Yaoliang Yu, Jaime G. Carbonell, Suvrit Sra.
    In NIPS 2014. Full paper, Bibtex.
  • "Saddle Points and Accelerated Perceptron Algorithms". (Full oral, INFORMS Data Mining Best Student Paper Finalist)
    Adams Wei Yu, Fatma Kılınç-Karzan, Jaime G. Carbonell.
    In ICML 2014. Full paper, Bibtex, Code.
  • "Reverse Top-k Search using Random Walk with Restart". (Full oral)
    Adams Wei Yu, Nikos Mamoulis, Hao Su.
    In VLDB 2014. Full paper, Technical report, Bibtex.
  • "Efficient Euclidean Projections onto the Intersection of Norm Balls". (Full oral)
    Adams Wei Yu*, Hao Su*, Li Fei-Fei. (* Indicates equal contribution)
    In ICML 2012. Full paper, Bibtex.
  • "Search by Mobile Image Based on Visual and Spatial Consistency". (Oral, Best Paper Nomination)
    Xianglong Liu, Yihua Lou, Adams Wei Yu, Bo Lang.
    In ICME 2011. Full paper, Bibtex.

Professional Activities

  • Organizing Committee: Workflow Chair, AISTATS 2017.
  • Journal Reviewer: JMLR, VLDBJ, TKDE, Neurocomputing.
  • Regular Conference Program Committee (Reviewer): ICML, NIPS, ICLR, KDD, AISTATS, AAAI, ALT.
  • Student Coordinator: CMU AI Seminar.
  • CMU MLD PhD admission committee, 2017, 2018.

Teaching Experience