About Me

My Photo

Contact Information

5138 Upson Hall
Dept. of Computer Science
Cornell University
Email: cnyu AT cs.cornell.edu
Office: (607) 255-9201

I am a Ph.d. candidate at the Dept. of Computer Science at Cornell University. My advisor is Thorsten Joachims. Prior to coming to Cornell, I spent three enjoyable years at Wadham College, Oxford, earning a BA degree in Mathematics and Computer Science.
I am graduating in May 2010. Here is my CV.

Research Interests.

My main research area is structured output prediction, especially methods based on large-margin principles. I also work on support vector machines, kernel methods, and on the large-scale training of these models.

Publications.

    • Predicting Structured Objects with Support Vector Machines
    • T. Joachims, T. Hofmann, Y. Yue and C.-N. Yu
    • Communications of the ACM, Research Highlight, 52(11):97-104, November 2009
    • Sparse Kernel SVMs via Cutting-Plane Training (pdf)
    • T. Joachims and C.-N. Yu
    • ECML PKDD 2009 special issue, Machine Learning Journal
    • (Best Machine Learning Paper Award)
    • Learning Structural SVMs with Latent Variables (pdf) (code)
    • C.-N. Yu and T. Joachims
    • International Conference on Machine Learning (ICML), 2009
    • (An earlier version appeared in NIPS 2008 Structured Input-Structured Output Workshop (pdf) )
    • Cutting-Plane Training of Structural SVMs (pdf)
    • T. Joachims, T. Finley and C.-N. Yu
    • Machine Learning Journal, 77(1):27-59
    • Training Structural SVMs with Kernels Using Sampled Cuts (pdf) (software)
    • C.-N. Yu and T. Joachims
    • Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 2008
    • Support Vector Training of Protein Alignment Models (pdf) (software)
    • C.-N. Yu, T. Joachims, R. Elber, J. Pillardy
    • Proceedings of the International Conference in Research in Computational Biology (RECOMB), 2007
    • Training Protein Threading Models using Structural SVMs (pdf)
    • C.-N. Yu, T. Joachims, R. Elber
    • ICML Workshop on Learning in Structured Output Spaces, 2006