Photo

Hi, this is Yatao (name). I am a PhD candidate in the Institute for Machine Learning at ETH Zürich. I am supervised by Prof. Joachim M. Buhmann and also work closely with Prof. Andreas Krause (PhD co-examiner). Before that I obtained my M.Sc.Eng. and B.Sc.Eng. from Shanghai Jiao Tong University.

I am currently interested in topics including machine learning, continuous & combinatorial optimization and decentralized AI. I like various sports, e.g., swimming, running, hiking & skiing.

Contact:       Bian's email
ORCID:           orcid.org/0000-0002-2368-4084




News

  • Apr. 2019: paper accepted by ICML19.
  • Oct. 2018: papers accepted by NeurIPS18 and BNP@NeurIPS18.
  • Sep. 2017: paper "Continuous DR-submodular Maximization: Structure and Algorithms" accepted by NIPS17.
  • Since June 2015, I am associated Fellow of the Max Planck ETH Center for Learning Systems.

Teaching

Courses@ETH Zürich

  • TA to Prof. Thomas Hofmann
    "Computational intelligence lab" (Spring 2018)
  • TA to Prof. Joachim M. Buhmann
    "Machine Learning" (Fall 2017) [website]
  • TA to Prof. Thomas Hofmann
    "Computational intelligence lab" (Spring 2017) [website]
  • TA to Prof. Joachim M. Buhmann
    "Machine Learning" (Fall 2016)
  • TA to Prof. Thomas Hofmann
    "Computational intelligence lab" (Spring 2016) [website]
  • TA to Prof. Joachim M. Buhmann
    "Machine Learning" (Fall 2015)
  • TA to Prof. Joachim M. Buhmann
    "Introduction to Machine Learning" (Fall 2014)

Papers & Code

Copyright warning: The copyright of each published paper belongs to the respective publisher. The local copy is only for non-commercial, personal use.

Activities

Paper Reviewing

  • NIPS 2019, ICML2019, AISTATS 2019, STOC 2018, ITCS 2017, NIPS 2016

Research Projects

Fast Human Motion Tracking (National Champion in China Accelerated Computing Contest, 2011)
In charge of PAPF design, GPU implementation and optimization.
Proposed Parallelized Annealed Particle Filter (PAPF) algorithm via heterogeneous computing and built a real-time marker-less motion tracking system. Achieved 399 times speedup.


3D Monocular Human Upper Body Pose Estimation (Samsung Corp. Cooperate)
Team leader. Algorithm design, implementation and optimization.
Conducted human upper body pose estimation via generative algorithms . Incorporating generative models and discriminative algorithms to pursue better performance.

Metal Parts Detection and Rustiness Estimation Under Complex Background (NTT Corp. Cooperate)
Team leader. Algorithm design, implementation and optimization.
Solved the problem of multi-view metal parts detection by training multiple templates. Used a novel template representation based on locally dominant gradient orientations.

Links

(Non-)Convex Optimization

Machine Learning

MISC