Yisong Yue - Research
Home - Research - About - Potpourri

My research interests lie primarily in the theory and application of statistical machine learning. I am currently a visiting researcher at Disney Research. In Fall 2014, I will be starting as an assistant professor in the Computing and Mathematical Sciences Department at the California Institute of Technology.

I was previously a postdoctoral researcher in the Machine Learning Department and the iLab at Carnegie Mellon University, where I worked with Carlos Guestrin and Ramayya Krishnan. I received my Ph.D. from the Computer Science Department at Cornell University, and my advisor was Thorsten Joachims.

Jump to: [publications] - [tutorials] - [other talk materials] - [research word cloud]

  • Graduate Admissions @ Caltech

  • Postdoc Openings @ Caltech

  • Curriculum Vitae

  • Self-Improving Systems that Learn Through Human Interaction - a popular-science blog article I wrote.


    Research Interests:
  • Structured Prediction - how can we model complex interdependencies to make more accurate predictions?
  • Text Classification & Information Extraction - how can we deduce the salient information embedded in textual data?
  • Diversified Retrieval - how can we make diverse and novel recommendations to improve utility to users?
  • Interactive Systems - how can we model the entire interaction experience between users and the system?
  • Online Algorithms - how can we design algorithms that can perform well when they learn "on the fly"?
  • Implicit Feedback - how can we best interpret and leverage observed user behaviors to train smarter systems?


    Software:
  • SVMsle - this is a Support Vector Machine method for learning to predict document-level sentiment polarity using latent explanations.
  • SVMdiv - this is a Support Vector Machine method for learning to predict diverse subsets for subtopic retrieval.
  • SVMmap - this is a Support Vector Machine method for learning ranking functions that that optimize for mean average precision.


    Professional Activities:
    Note - Henceforth, I refuse to be a reviewer or editor for any Elsevier journal for reasons described here.

    Journal Reviewer
  • Data Mining and Knowledge Discovery
  • Information Processing & Management
  • Information Retrieval
  • Journal of Artificial Intelligence Research
  • Neural Networks
  • Transactions on Knowledge and Data Engineering
  • Transactions on the Web

    Conference Program Committee / Reviewer
  • AAAI 2014
  • ACL 2012
  • ACML 2011, 2012
  • CIKM 2012
  • COLING 2010, 2014
  • ECML/PKDD 2008
  • EMNLP 2011, 2012
  • ICML 2007, 2008, 2009, 2010, 2011, 2012, 2013 (Area Chair), 2014
  • KDD 2011
  • NAACL-HLT 2012, 2013
  • NIPS 2008, 2009, 2010, 2011, 2012, 2014
  • SIGIR 2008, 2009, 2010, 2013, 2014
  • SoCG 2010
  • UBICOMP 2014
  • WSDM 2011, 2012, 2013, 2014
  • WWW 2011, 2012, 2013, 2014


    Publications:
  • Yisong Yue, Chong Wang, Khalid El-Arini, Carlos Guestrin, Personalized Collaborative Clustering, International World Wide Web Conference (WWW), April, 2014.
    [pdf][slides]

  • Alina Bialkowski, Patrick Lucey, Peter Carr, Yisong Yue, Iain Matthews, "Win at Home and Draw Away": Automatic Formation Analysis Highlighting the Differences in Home and Away Team Behaviors, MIT Sloan Sports Analytics Conference (SSAC), February, 2014.
    [pdf]

  • Patrick Lucey, Alina Bialkowski, Peter Carr, Yisong Yue, Iain Matthews, "How to Get an Open Shot": Analyzing Team Movement in Basketball using Tracking Data, MIT Sloan Sports Analytics Conference (SSAC), February, 2014.
    [pdf]

  • Siyuan Liu, Yisong Yue, Ramayya Krishnan, Adaptive Collective Routing Using Gaussian Process Dynamic Congestion Models, ACM Conference on Knowledge Discovery and Data Mining (KDD), August, 2013.
    [pdf]

  • Jiaji Zhou, Stephane Ross, Yisong Yue, Debadeepta Dey, J. Andrew Bagnell, Knapsack Constrained Contextual Submodular List Prediction with Application to Multi-document Summarization, ICML Workshop on Inferning: Interactions between Inference and Learning, June, 2013.
    [pdf][software]

  • Stephane Ross, Jiaji Zhou, Yisong Yue, Debadeepta Dey, J. Andrew Bagnell, Learning Policies for Contextual Submodular Prediction, International Conference on Machine Learning (ICML), June, 2013.
    [pdf][long][software][video]

  • Yisong Yue, Lavanya Marla, Ramayya Krishnan, An Efficient Simulation-based Approach to Ambulance Fleet Allocation and Dynamic Redeployment, AAAI Conference on Artificial Intelligence (AAAI), Special Track on Computational Sustainability and Artificial Intelligence, July, 2012.
    [pdf][spotlight slide][poster][press release]

  • Yisong Yue, Sue Ann Hong, Carlos Guestrin, Hierarchical Exploration for Accelerating Contextual Bandits, International Conference on Machine Learning (ICML), June, 2012.
    [pdf][long][slides][poster][video]

  • Yisong Yue, Josef Broder, Robert Kleinberg, Thorsten Joachims, The K-armed Dueling Bandits Problem, Journal of Computer and System Sciences (JCSS), Special Issue on Learning Theory, doi:10.1016/j.jcss.2011.12.028, May, 2012.
    [pdf][online]

  • Olivier Chapelle, Thorsten Joachims, Filip Radlinski, Yisong Yue, Large Scale Validation and Analysis of Interleaved Search Evaluation, ACM Transactions on Information Systems (TOIS), 30(1), 6:1--6:41, February, 2012.
    [pdf]

  • Yisong Yue, Carlos Guestrin, Linear Submodular Bandits and their Application to Diversified Retrieval, Neural Information Processing Systems (NIPS), December, 2011.
    [pdf][long][poster]

  • Yisong Yue, Thorsten Joachims, Beat the Mean Bandit, International Conference on Machine Learning (ICML), June, 2011.
    [pdf][slides][poster][video]

  • Christina Brandt, Thorsten Joachims, Yisong Yue, Jacob Bank, Dynamic Ranked Retrieval, ACM Conference on Web Search and Data Mining (WSDM), February, 2011. (Best Paper Nomination)
    [pdf][software][video]

  • Yisong Yue, New Learning Frameworks for Information Retrieval, Ph.D. Dissertation, Cornell University, January, 2011.
    [pdf]

  • Ainur Yessenalina, Yisong Yue, Claire Cardie, Multi-level Structured Models for Document-level Sentiment Classification, Conference on Empirical Methods in Natural Language Processing (EMNLP), October, 2010.
    [pdf][software][data]

  • Yisong Yue, Yue Gao, Olivier Chapelle, Ya Zhang, Thorsten Joachims, Learning More Powerful Test Statistics for Click-Based Retrieval Evaluation, ACM Conference on Information Retrieval (SIGIR), July, 2010.
    [pdf][slides]

  • Yisong Yue, Rajan Patel, Hein Roehrig, Beyond Position Bias: Examining Result Attractiveness as a Source of Presentation Bias in Clickthrough Data, World Wide Web Conference (WWW), April, 2010.
    [pdf][slides]

  • Thorsten Joachims, Thomas Hofmann, Yisong Yue, Chun-Nam Yu, Predicting Structured Objects with Support Vector Machines, Communications of the ACM (CACM), Research Highlight, 52(11), 97--104, November, 2009. (with a technical perspective by John Shawe-Taylor)
    [pdf][online]

  • Yisong Yue, Josef Broder, Robert Kleinberg, Thorsten Joachims, The K-armed Dueling Bandits Problem, Conference on Learning Theory (COLT), June, 2009.
    [pdf][slides]

  • Yisong Yue, Thorsten Joachims, Interactively Optimizing Information Retrieval Systems as a Dueling Bandits Problem, International Conference on Machine Learning (ICML), June, 2009.
    [pdf][slides][video]

  • Yisong Yue, Thorsten Joachims, Predicting Diverse Subsets Using Structural SVMs, International Conference on Machine Learning (ICML), June, 2008.
    [pdf][slides][software][video]

  • Yisong Yue, Christopher Burges, On Using Simultaneous Perturbation Stochastic Approximation for IR Measures, and the Empirical Optimality of LambdaRank, NIPS Machine Learning for Web Search Workshop, December, 2007.
    [pdf][tech report]

  • Yisong Yue, Thomas Finley, Filip Radlinski, Thorsten Joachims, A Support Vector Method for Optimizing Average Precision, ACM Conference on Information Retrieval (SIGIR), July, 2007.
    [pdf][slides][software]


    Tutorials:
  • An Introduction to Ensemble Methods: Bagging, Boosting, Random Forests and More, presented at Disney Research. [slides]
  • Practical Online Retrieval Evaluation, co-taught with Filip Radlinski, presented at SIGIR 2011. [slides][demo scripts]
  • Learning to Rank, co-taught with Filip Radlinski, presented at NESCAI 2008. [part1][part2]


    Other Talk Materials:
  • Balancing the Explore/Exploit Tradeoff in Interactive Structured Prediction, NIPS 2013 Workshop on Discrete and Combinatorial Problems in Machine Learning, December, 2013. [slides]
  • Learning with Humans in the Loop, Disney Research, May, 2013. [slides]
  • Optimizing Recommender Systems as a Submodular Bandit Problem, University of Toronto, November, 2012. [slides]
  • An Introduction to Structural SVMs and its Application to Information Retrieval, University of California Berkeley, October, 2012. [slides]
  • Practical and Reliable Retrieval Evaluation Through Online Experimentation, WSDM 2012 Workshop on Web Search Click Data, February, 2012. [slides]
  • An Interactive Learning Approach to Optimizing Information Retrieval Systems, Carnegie Mellon University, September, 2010. [slides][video]
  • New Learning Frameworks for Information Retrieval, Microsoft Research, March, 2010. [video]
  • Diversified Retrieval as Structured Prediction, SIGIR 2009 Workshop on Redundancy, Diversity and Interdependent Document Relevance, July, 2009. [slides]
  • Information Retrieval as Structured Prediction, University of Massachusetts Amherst, April, 2009. [slides]


    Teaching Assistant Experience:
  • Fall 2007, CS 473 - AI Practicum / Robotics and Embodied AI
  • Spring 2007, INFO 204 - Networks [received TA excellence award]
  • Fall 2006, CS 578 - Empirical Methods in Machine Learning and Data Mining
  • Fall 2005 - Spring 2006, CS 100M - Introduction to Computer Programming [Teaching Evaluation] [received TA excellence award]




  • Home - Research - About - Potpourri
    [All Content © 2014 Yisong Yue]