Research Interests
My research is largely centered around developing integrated learning-based approaches that can characterize complex structured and adaptive decision-making settings. My interests span across both applied and theoretical research pursuits. Specific research areas include:
  • Interactive Systems - how can we model the entire interaction sequence between the system and its environment?
  • Structured Prediction - how can we model complex interdependencies to make more accurate predictions?
  • Human-in-the-Loop - how can we reason about systems that learn from and interact with humans?
  • Spatiotemporal Reasoning - how can we reason about raw spatiotemporal data to build more compact and accurate models?
[curriculum vitae]
Projects & Focus Areas
Note that focus areas are typically overlapping, and many published papers span multiple focus areas.
  • Learning to Optimize - we aim to learn customized solvers to tackle focused distributions of optimization problems. Our interests span both continuous (e.g., amortized optimization) and discrete optimization (e.g., learning to branch-and-bound).
    More Info
    • Learning to Search via Retrospective Imitation
      Jialin Song, Ravi Lanka, Albert Zhao, Yisong Yue, Masahiro Ono
      [arxiv]
    • A General Method for Amortizing Variational Filtering
      Joseph Marino, Milan Cvitkovic, Yisong Yue
      Neural Information Processing Systems (NIPS), December 2018.
      (pdf forthcoming)
    • Iterative Amortized Inference
      Joseph Marino, Yisong Yue, Stephan Mandt
      International Conference on Machine Learning (ICML), July 2018.
      [pdf][long]
    • Knapsack Constrained Contextual Submodular List Prediction with Application to Multi-document Summarization
      Jiaji Zhou, Stephane Ross, Yisong Yue, Debadeepta Dey, J. Andrew Bagnell
      ICML Workshop on Inferning: Interactions between Inference and Learning, June, 2013.
      [pdf][software]
    • Learning Policies for Contextual Submodular Prediction
      Stephane Ross, Jiaji Zhou, Yisong Yue, Debadeepta Dey, J. Andrew Bagnell
      International Conference on Machine Learning (ICML), June, 2013.
      [pdf][long][software][video]
  • Structured Imitation Learning - we aim to develop imitation learning algorithms that can incorporate structural assumptions to improve the effectiveness of learning. Examples include blending with graphical models to encode conditional independence assumptions, blending with model-based controllers to ensure various stability properties, and hierarchial learning to plan over lon time horizons.
    More Info
    • Learning to Search via Retrospective Imitation
      Jialin Song, Ravi Lanka, Albert Zhao, Yisong Yue, Masahiro Ono
      [arxiv]
    • Generative Multi-Agent Behavioral Cloning
      Eric Zhan, Stephan Zheng, Yisong Yue, Long Sha, Patrick Lucey
      [arxiv][demo][code]
    • Hierarchical Imitation and Reinforcement Learning
      Hoang M. Le, Nan Jiang, Alekh Agarwal, Miroslav Dudík, Yisong Yue, Hal Daumé III
      International Conference on Machine Learning (ICML), July 2018.
      [pdf][long][arxiv][project]
    • Iterative Amortized Inference
      Joseph Marino, Yisong Yue, Stephan Mandt
      International Conference on Machine Learning (ICML), July 2018.
      [pdf][long]
    • Coordinated Multi-Agent Imitation Learning
      Hoang M. Le, Yisong Yue, Peter Carr, Patrick Lucey
      International Conference on Machine Learning (ICML), August 2017.
      [pdf][long][arxiv][data][press release]
    • Learning recurrent representations for hierarchical behavior modeling
      Eyrun Eyjolfsdottir, Kristin Branson, Yisong Yue, Pietro Perona
      International Conference on Learning Representations (ICLR), April, 2017.
      [pdf][arxiv][supplementary]
    • Data-Driven Ghosting using Deep Imitation Learning
      Hoang M. Le, Peter Carr, Yisong Yue, Patrick Lucey
      MIT Sloan Sports Analytics Conference (SSAC), March, 2017.
      (Best Paper Nomination)
      [pdf][project][demo video][press release]
    • Generating Long-term Trajectories Using Deep Hierarchical Networks
      Stephan Zheng, Yisong Yue, Patrick Lucey
      Neural Information Processing Systems (NIPS), December, 2016.
      [pdf][long][data]
    • Learning Online Smooth Predictors for Real-time Camera Planning using Recurrent Decision Trees
      Jianhui Chen, Hoang M. Le, Peter Carr, Yisong Yue, James J. Little
      IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2016.
      (Oral Presentation)
      [pdf][long][press release][Sports Illustrated][DataScience.com]
    • Smooth Imitation Learning for Online Sequence Prediction
      Hoang M. Le, Andrew Kang, Yisong Yue, Peter Carr
      International Conference on Machine Learning (ICML), June, 2016.
      [pdf][long][video][press release][Sports Illustrated][DataScience.com]
    • Knapsack Constrained Contextual Submodular List Prediction with Application to Multi-document Summarization
      Jiaji Zhou, Stephane Ross, Yisong Yue, Debadeepta Dey, J. Andrew Bagnell
      ICML Workshop on Inferning: Interactions between Inference and Learning, June, 2013.
      [pdf][software]
    • Learning Policies for Contextual Submodular Prediction
      Stephane Ross, Jiaji Zhou, Yisong Yue, Debadeepta Dey, J. Andrew Bagnell
      International Conference on Machine Learning (ICML), June, 2013.
      [pdf][long][software][video]
  • Spatiotemporal Sequence Modeling - we aim to learn models that can reason over complex spatiotemporal sequences. Problems of interest include forecasting, generation, and conditioning on complex contextual inputs.
    More Info
    • PhaseLink: A Deep Learning Approach to Seismic Phase Association
      Zachary Ross, Yisong Yue, Men-Andrin Meier, Egill Hauksson, Thomas Heaton
      [arxiv]
    • Generative Multi-Agent Behavioral Cloning
      Eric Zhan, Stephan Zheng, Yisong Yue, Long Sha, Patrick Lucey
      [arxiv][demo][code]
    • Long-term Forecasting using Tensor-Train RNNs
      Rose Yu, Stephan Zheng, Anima Anandkumar, Yisong Yue
      [arxiv][code]
    • A Deep Learning Approach for Generalized Speech Animation
      Sarah Taylor, Taehwan Kim, Yisong Yue, Moshe Mahler, James Krahe, Anastasio Garcia Rodriguez, Jessica Hodgins, Iain Matthews
      ACM Conference on Computer Graphics (SIGGRAPH), July 2017.
      [pdf][long][demo video]
    • Generating Long-term Trajectories Using Deep Hierarchical Networks
      Stephan Zheng, Yisong Yue, Patrick Lucey
      Neural Information Processing Systems (NIPS), December, 2016.
      [pdf][long][data]
    • A Decision Tree Framework for Spatiotemporal Sequence Prediction
      Taehwan Kim, Yisong Yue, Sarah Taylor, Iain Matthews
      ACM Conference on Knowledge Discovery and Data Mining (KDD), August, 2015.
      [pdf][demo]
  • Machine Teaching - we aim to develop novel algorithms for automated machine teaching, where the goal is for the machine to select examples to teach a human. Problems of interest include adaptive teaching for forgetful learners, and interpretable teaching with explanations.
    More Info
    • Teaching Multiple Concepts to Forgetful Learners
      Anette Hunziker, Yuxin Chen, Oisin Mac Aodha, Manuel Gomez Rodriguez, Andreas Krause, Pietro Perona, Yisong Yue, Adish Singla
      [arxiv]
    • Understanding the Role of Adaptivity in Machine Teaching: The Case of Version Space Learners
      Yuxin Chen, Adish Singla, Oisin Mac Aodha, Pietro Perona, Yisong Yue
      Neural Information Processing Systems (NIPS), December 2018.
      [arxiv]
    • Teaching Categories to Human Learners with Visual Explanations
      Oisin Mac Aodha, Shihan Su, Yuxin Chen, Pietro Perona, Yisong Yue
      IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018.
      [arxiv]
    • Near-Optimal Machine Teaching via Explanatory Teaching Sets
      Yuxin Chen, Oisin Mac Aodha, Shihan Su, Pietro Perona, Yisong Yue
      International Conference on Artificial Intelligence and Statistics (AISTATS), April 2018.
      [pdf][long]
  • Certifiable Learning - we aim to develop learning algorithms with certifiable guarantees such as safety, robustness, or stability.
    More Info
    • Detecting Adversarial Examples via Neural Fingerprinting
      Sumanth Dathathri, Stephan Zheng, Richard M. Murray, Yisong Yue
      [arxiv][code]
    • Stagewise Safe Bayesian Optimization with Gaussian Processes
      Yanan Sui, Vincent Zhuang, Joel Burdick, Yisong Yue
      International Conference on Machine Learning (ICML), July 2018.
      [pdf][long][arxiv]
    • Safe Exploration and Optimization of Constrained MDPs using Gaussian Processes
      Akifumi Wachi, Yanan Sui, Yisong Yue, Masahiro Ono
      AAAI Conference on Artificial Intelligence (AAAI), February 2018.
      [pdf]
    • Smooth Imitation Learning for Online Sequence Prediction
      Hoang M. Le, Andrew Kang, Yisong Yue, Peter Carr
      International Conference on Machine Learning (ICML), June, 2016.
      [pdf][long][video][press release][Sports Illustrated][DataScience.com]
  • Interpretable Machine Learning - we aim to design models that are interpretable to humans. Two common paradigms are models that are statically interpretable (e.g., with some low-dimensional bottleneck that is easy to visualize), and models that give interpretable predictions (e.g., with explanations).
    More Info
    • Multi-resolution Tensor Learning for Large-Scale Spatial Data
      Stephan Zheng, Rose Yu, Yisong Yue
      [arxiv]
    • Teaching Categories to Human Learners with Visual Explanations
      Oisin Mac Aodha, Shihan Su, Yuxin Chen, Pietro Perona, Yisong Yue
      IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018.
      [arxiv]
    • Near-Optimal Machine Teaching via Explanatory Teaching Sets
      Yuxin Chen, Oisin Mac Aodha, Shihan Su, Pietro Perona, Yisong Yue
      International Conference on Artificial Intelligence and Statistics (AISTATS), April 2018.
      [pdf][long]
    • Factorized Variational Autoencoders for Modeling Audience Reactions to Movies
      Zhiwei Deng, Rajitha Navarathna, Peter Carr, Stephan Mandt, Yisong Yue, Iain Matthews, Greg Mori
      IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July, 2017.
      [pdf][press release][radio interview]
    • Learning Fine-Grained Spatial Models for Dynamic Sports Play Prediction
      Yisong Yue, Patrick Lucey, Peter Carr, Alina Bialkowski, Iain Matthews
      IEEE International Conference on Data Mining (ICDM), December, 2014.
      (Best Paper Nomination)
      [pdf][demo][press release]
    • Multi-level Structured Models for Document-level Sentiment Classification
      Ainur Yessenalina, Yisong Yue, Claire Cardie
      Conference on Empirical Methods in Natural Language Processing (EMNLP), October, 2010.
      [pdf][software][data]
  • Preference Learning - we aim to design learning algorithms that learn from preference feedback (e.g., is A better than B?) rather than typical cardinal feedback (e.g., how good is A?). Preference feedback is often more reliable than cardinal feedback when eliciting subjective feedback from humans.
    More Info
    • Advancements in Dueling Bandits
      Yanan Sui, Masrour Zoghi, Katja Hofmann, Yisong Yue
      International Joint Conference on Artificial Intelligence (IJCAI), Survey Track, July 2018.
      [pdf]
    • Stagewise Safe Bayesian Optimization with Gaussian Processes
      Yanan Sui, Vincent Zhuang, Joel Burdick, Yisong Yue
      International Conference on Machine Learning (ICML), July 2018.
      [pdf][long][arxiv]
    • Correlational Dueling Bandits with Application to Clinical Treatment in Large Decision Spaces
      Yanan Sui, Yisong Yue, Joel Burdick
      International Joint Conference on Artificial Intelligence (IJCAI), August 2017.
      [pdf][arxiv]
    • Multi-dueling Bandits with Dependent Arms
      Yanan Sui, Vincent Zhuang, Joel Burdick, Yisong Yue
      Conference on Uncertainty in Artificial Intelligence (UAI), August 2017.
      [pdf][long][arxiv]
    • Large-Scale Validation and Analysis of Interleaved Search Evaluation
      Olivier Chapelle, Thorsten Joachims, Filip Radlinski, Yisong Yue
      ACM Transactions on Information Systems (TOIS), 30(1), 6:1--6:41, February, 2012.
      (Selected for ACM Notable Computing Books and Articles of 2012)
      [pdf]
    • The K-armed Dueling Bandits Problem
      Yisong Yue, Josef Broder, Robert Kleinberg, Thorsten Joachims
      Journal of Computer and System Sciences (JCSS), Special Issue on Learning Theory, DOI:10.1016/j.jcss.2011.12.028, May, 2012.
      [pdf][online]
    • Beat the Mean Bandit
      Yisong Yue, Thorsten Joachims
      International Conference on Machine Learning (ICML), June, 2011.
      [pdf][slides][poster][video]
    • Learning More Powerful Test Statistics for Click-Based Retrieval Evaluation
      Yisong Yue, Yue Gao, Olivier Chapelle, Ya Zhang, Thorsten Joachims
      ACM Conference on Information Retrieval (SIGIR), July, 2010.
      [pdf][slides]
    • The K-armed Dueling Bandits Problem
      Yisong Yue, Josef Broder, Robert Kleinberg, Thorsten Joachims
      Conference on Learning Theory (COLT), June, 2009.
      [pdf][slides]
    • Interactively Optimizing Information Retrieval Systems as a Dueling Bandits Problem
      Yisong Yue, Thorsten Joachims
      International Conference on Machine Learning (ICML), June, 2009.
      [pdf][slides][video]
  • Dynamic Structured Prediction - we aim to design algorithms for structured prediction in dynamic settings. Technical challenges include balancing the exploration/exploitation tradeoff, and solving complex planning problems over time.
    More Info
    • Generative Multi-Agent Behavioral Cloning
      Eric Zhan, Stephan Zheng, Yisong Yue, Long Sha, Patrick Lucey
      [arxiv][demo][code]
    • Coordinated Multi-Agent Imitation Learning
      Hoang M. Le, Yisong Yue, Peter Carr, Patrick Lucey
      International Conference on Machine Learning (ICML), August 2017.
      [pdf][long][arxiv][data][press release]
    • Data-Driven Ghosting using Deep Imitation Learning
      Hoang M. Le, Peter Carr, Yisong Yue, Patrick Lucey
      MIT Sloan Sports Analytics Conference (SSAC), March, 2017.
      (Best Paper Nomination)
      [pdf][project][demo video][press release]
    • Smooth Interactive Submodular Set Cover
      Bryan He, Yisong Yue
      Neural Information Processing Systems (NIPS), December, 2015.
      [pdf][long]
    • Non-Myopic Adaptive Route Planning in Uncertain Congestion Environments
      Siyuan Liu, Yisong Yue, Ramayya Krishnan
      IEEE Transactions on Knowledge and Data Engineering (TKDE), 27(9), 2438--2451, DOI:10.1109/TKDE.2015.2411278, September, 2015.
      [preprint][online]
    • Adaptive Collective Routing Using Gaussian Process Dynamic Congestion Models
      Siyuan Liu, Yisong Yue, Ramayya Krishnan
      ACM Conference on Knowledge Discovery and Data Mining (KDD), August, 2013.
      [pdf]
    • An Efficient Simulation-based Approach to Ambulance Fleet Allocation and Dynamic Redeployment
      Yisong Yue, Lavanya Marla, Ramayya Krishnan
      AAAI Conference on Artificial Intelligence (AAAI), Special Track on Computational Sustainability and Artificial Intelligence, July, 2012.
      [pdf][spotlight slide][poster][press release][data]
    • Linear Submodular Bandits and their Application to Diversified Retrieval
      Yisong Yue, Carlos Guestrin
      Neural Information Processing Systems (NIPS), December, 2011.
      [pdf][long][poster]
  • Large Margin Structured Prediction - we aim to develop large-margin learning methods for structured prediction settings. Examples including learning rankings, submodular functions, and multi-level models.
    More Info
    • Multi-level Structured Models for Document-level Sentiment Classification
      Ainur Yessenalina, Yisong Yue, Claire Cardie
      Conference on Empirical Methods in Natural Language Processing (EMNLP), October, 2010.
      [pdf][software][data]
    • Predicting Structured Objects with Support Vector Machines
      Thorsten Joachims, Thomas Hofmann, Yisong Yue, Chun-Nam Yu
      Communications of the ACM (CACM), Research Highlight, 52(11), 97--104, November, 2009.
      (With a technical perspective by John Shawe-Taylor.)
      [pdf][online]
    • Predicting Diverse Subsets Using Structural SVMs
      Yisong Yue, Thorsten Joachims
      International Conference on Machine Learning (ICML), June, 2008.
      [pdf][slides][software][video]
    • A Support Vector Method for Optimizing Average Precision
      Yisong Yue, Thomas Finley, Filip Radlinski, Thorsten Joachims
      ACM Conference on Information Retrieval (SIGIR), July, 2007.
      [pdf][slides][software]
  • Implicit Human Feedback - we aim to better understand biases that affect how we interpret implicit human feedback, such as clicks on a ranked list of search results.
    More Info
    • Large-Scale Validation and Analysis of Interleaved Search Evaluation
      Olivier Chapelle, Thorsten Joachims, Filip Radlinski, Yisong Yue
      ACM Transactions on Information Systems (TOIS), 30(1), 6:1--6:41, February, 2012.
      (Selected for ACM Notable Computing Books and Articles of 2012)
      [pdf]
    • Learning More Powerful Test Statistics for Click-Based Retrieval Evaluation
      Yisong Yue, Yue Gao, Olivier Chapelle, Ya Zhang, Thorsten Joachims
      ACM Conference on Information Retrieval (SIGIR), July, 2010.
      [pdf][slides]
    • Beyond Position Bias: Examining Result Attractiveness as a Source of Presentation Bias in Clickthrough Data
      Yisong Yue, Rajan Patel, Hein Roehrig
      International World Wide Web Conference (WWW), April, 2010.
      [pdf][slides]
  • Richer User Interactions - we aim to develop methods that better capture the design space of interactions in richer user interfaces. We are interested in both learning from rich interaction feedback, and designing recommendation algorithms that better exploit such interfaces.
    More Info
    • Interactive Sports Analytics: An Intelligent Interface for Utilizing Trajectories for Interactive Sports Play Retrieval and Analytics
      Long Sha, Patrick Lucey, Yisong Yue, Xinyu Wei, Jennifer Hobbs, Charlie Rohlf, Sridha Sridharan
      ACM Transactions on Computer-Human Interaction (TOCHI), April 2018.
      [pdf]
    • Chalkboarding: A New Spatiotemporal Query Paradigm for Sports Play Retrieval
      Long Sha, Patrick Lucey, Yisong Yue, Peter Carr, Charlie Rohlf, Iain Matthews
      ACM Conference on Intelligent User Interfaces (IUI), March, 2016.
      [pdf][demo video][press release]
    • Personalized Collaborative Clustering
      Yisong Yue, Chong Wang, Khalid El-Arini, Carlos Guestrin
      International World Wide Web Conference (WWW), April, 2014.
      [pdf][slides][data]
    • Dynamic Ranked Retrieval
      Christina Brandt, Thorsten Joachims, Yisong Yue, Jacob Bank
      ACM Conference on Web Search and Data Mining (WSDM), February, 2011.
      (Best Paper Nomination)
      [pdf][software][video]
Preprints
  • PhaseLink: A Deep Learning Approach to Seismic Phase Association
    Zachary Ross, Yisong Yue, Men-Andrin Meier, Egill Hauksson, Thomas Heaton
    [arxiv]
  • Teaching Multiple Concepts to Forgetful Learners
    Anette Hunziker, Yuxin Chen, Oisin Mac Aodha, Manuel Gomez Rodriguez, Andreas Krause, Pietro Perona, Yisong Yue, Adish Singla
    [arxiv]
  • Learning to Search via Retrospective Imitation
    Jialin Song, Ravi Lanka, Albert Zhao, Yisong Yue, Masahiro Ono
    [arxiv]
  • Detecting Adversarial Examples via Neural Fingerprinting
    Sumanth Dathathri, Stephan Zheng, Richard M. Murray, Yisong Yue
    [arxiv][code]
  • Long-term Forecasting using Tensor-Train RNNs
    Rose Yu, Stephan Zheng, Anima Anandkumar, Yisong Yue
    [arxiv][code]
  • Generative Multi-Agent Behavioral Cloning
    Eric Zhan, Stephan Zheng, Yisong Yue, Long Sha, Patrick Lucey
    [arxiv][demo][code]
  • Multi-resolution Tensor Learning for Large-Scale Spatial Data
    Stephan Zheng, Rose Yu, Yisong Yue
    [arxiv]

All Publications
  • A General Method for Amortizing Variational Filtering
    Joseph Marino, Milan Cvitkovic, Yisong Yue
    Neural Information Processing Systems (NIPS), December 2018.
    (pdf forthcoming)
  • Understanding the Role of Adaptivity in Machine Teaching: The Case of Version Space Learners
    Yuxin Chen, Adish Singla, Oisin Mac Aodha, Pietro Perona, Yisong Yue
    Neural Information Processing Systems (NIPS), December 2018.
    [arxiv]
  • Advancements in Dueling Bandits
    Yanan Sui, Masrour Zoghi, Katja Hofmann, Yisong Yue
    International Joint Conference on Artificial Intelligence (IJCAI), Survey Track, July 2018.
    [pdf]
  • Iterative Amortized Inference
    Joseph Marino, Yisong Yue, Stephan Mandt
    International Conference on Machine Learning (ICML), July 2018.
    [pdf][long][arxiv]
  • Hierarchical Imitation and Reinforcement Learning
    Hoang M. Le, Nan Jiang, Alekh Agarwal, Miroslav Dudík, Yisong Yue, Hal Daumé III
    International Conference on Machine Learning (ICML), July 2018.
    [pdf][long][arxiv][project]
  • Stagewise Safe Bayesian Optimization with Gaussian Processes
    Yanan Sui, Vincent Zhuang, Joel Burdick, Yisong Yue
    International Conference on Machine Learning (ICML), July 2018.
    [pdf][long][arxiv]
  • Teaching Categories to Human Learners with Visual Explanations
    Oisin Mac Aodha, Shihan Su, Yuxin Chen, Pietro Perona, Yisong Yue
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018.
    [arxiv]
  • Interactive Sports Analytics: An Intelligent Interface for Utilizing Trajectories for Interactive Sports Play Retrieval and Analytics
    Long Sha, Patrick Lucey, Yisong Yue, Xinyu Wei, Jennifer Hobbs, Charlie Rohlf, Sridha Sridharan
    ACM Transactions on Computer-Human Interaction (TOCHI), April 2018.
    [pdf]
  • Near-Optimal Machine Teaching via Explanatory Teaching Sets
    Yuxin Chen, Oisin Mac Aodha, Shihan Su, Pietro Perona, Yisong Yue
    International Conference on Artificial Intelligence and Statistics (AISTATS), April 2018.
    [pdf][long]
  • Safe Exploration and Optimization of Constrained MDPs using Gaussian Processes
    Akifumi Wachi, Yanan Sui, Yisong Yue, Masahiro Ono
    AAAI Conference on Artificial Intelligence (AAAI), February 2018.
    [pdf]
  • Telemetry Anomaly Detection System using Machine Learning to Streamline Mission Operations
    Michela Munoz Fernandez, Yisong Yue, Romann Weber
    IEEE International Conference on Space Mission Challenges for Information Technology (SMC-IT), September 2017.
    [pdf]
  • Correlational Dueling Bandits with Application to Clinical Treatment in Large Decision Spaces
    Yanan Sui, Yisong Yue, Joel Burdick
    International Joint Conference on Artificial Intelligence (IJCAI), August 2017.
    [pdf][arxiv]
  • Multi-dueling Bandits with Dependent Arms
    Yanan Sui, Vincent Zhuang, Joel Burdick, Yisong Yue
    Conference on Uncertainty in Artificial Intelligence (UAI), August 2017.
    [pdf][long][arxiv]
  • Coordinated Multi-Agent Imitation Learning
    Hoang M. Le, Yisong Yue, Peter Carr, Patrick Lucey
    International Conference on Machine Learning (ICML), August 2017.
    [pdf][long][arxiv][data][press release]
  • A Deep Learning Approach for Generalized Speech Animation
    Sarah Taylor, Taehwan Kim, Yisong Yue, Moshe Mahler, James Krahe, Anastasio Garcia Rodriguez, Jessica Hodgins, Iain Matthews
    ACM Conference on Computer Graphics (SIGGRAPH), July 2017.
    [pdf][long][demo video]
  • Factorized Variational Autoencoders for Modeling Audience Reactions to Movies
    Zhiwei Deng, Rajitha Navarathna, Peter Carr, Stephan Mandt, Yisong Yue, Iain Matthews, Greg Mori
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July, 2017.
    [pdf][press release][radio interview]
  • Learning recurrent representations for hierarchical behavior modeling
    Eyrun Eyjolfsdottir, Kristin Branson, Yisong Yue, Pietro Perona
    International Conference on Learning Representations (ICLR), April, 2017.
    [pdf][arxiv][supplementary]
  • Data-Driven Ghosting using Deep Imitation Learning
    Hoang M. Le, Peter Carr, Yisong Yue, Patrick Lucey
    MIT Sloan Sports Analytics Conference (SSAC), March, 2017.
    (Best Paper Nomination)
    [pdf][project][demo video][press release]
  • A Rotation Invariant Latent Factor Model for Moveme Discovery from Static Poses
    Matteo Ronchi, Joon Sik Kim, Yisong Yue
    IEEE International Conference on Data Mining (ICDM), December, 2016.
    [pdf][long][project]
  • Generating Long-term Trajectories Using Deep Hierarchical Networks
    Stephan Zheng, Yisong Yue, Patrick Lucey
    Neural Information Processing Systems (NIPS), December, 2016.
    [pdf][long][data]
  • Learning Online Smooth Predictors for Real-time Camera Planning using Recurrent Decision Trees
    Jianhui Chen, Hoang M. Le, Peter Carr, Yisong Yue, James J. Little
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2016.
    (Oral Presentation)
    [pdf][long][press release][Sports Illustrated][DataScience.com]
  • Smooth Imitation Learning for Online Sequence Prediction
    Hoang M. Le, Andrew Kang, Yisong Yue, Peter Carr
    International Conference on Machine Learning (ICML), June, 2016.
    [pdf][long][video][press release][Sports Illustrated][DataScience.com]
  • Chalkboarding: A New Spatiotemporal Query Paradigm for Sports Play Retrieval
    Long Sha, Patrick Lucey, Yisong Yue, Peter Carr, Charlie Rohlf, Iain Matthews
    ACM Conference on Intelligent User Interfaces (IUI), March, 2016.
    [pdf][demo video][press release]
  • Robust Ambulance Allocation Using Risk-based Metrics
    Kaushik Krishnan, Lavanya Marla, Yisong Yue
    COMSNETS 2016 Workshop on Intelligence Transportation Systems, January, 2016.
    [pdf]
  • Scalable Training of Interpretable Spatial Latent Factor Models
    Stephan Zheng, Yisong Yue
    NIPS 2015 Workshop on Non-convex Optimization for Machine Learning, December, 2015.
    [pdf]
  • Smooth Interactive Submodular Set Cover
    Bryan He, Yisong Yue
    Neural Information Processing Systems (NIPS), December, 2015.
    [pdf][long]
  • Non-Myopic Adaptive Route Planning in Uncertain Congestion Environments
    Siyuan Liu, Yisong Yue, Ramayya Krishnan
    IEEE Transactions on Knowledge and Data Engineering (TKDE), 27(9), 2438--2451, DOI:10.1109/TKDE.2015.2411278, September, 2015.
    [preprint][online]
  • A Decision Tree Framework for Spatiotemporal Sequence Prediction
    Taehwan Kim, Yisong Yue, Sarah Taylor, Iain Matthews
    ACM Conference on Knowledge Discovery and Data Mining (KDD), August, 2015.
    [pdf][demo]
  • Identifying Team Style in Soccer using Formations Learned from Spatiotemporal Tracking Data
    Alina Bialkowski, Patrick Lucey, Peter Carr, Yisong Yue, Sridha Sridharan, Iain Matthews
    ICDM 2014 International Workshop on Spatial and Spatio-temporal Data Mining (SSTDM), December, 2014.
    [pdf]
  • Learning Fine-Grained Spatial Models for Dynamic Sports Play Prediction
    Yisong Yue, Patrick Lucey, Peter Carr, Alina Bialkowski, Iain Matthews
    IEEE International Conference on Data Mining (ICDM), December, 2014.
    (Best Paper Nomination)
    [pdf][demo][press release]
  • Large-Scale Analysis of Soccer Matches using Spatiotemporal Tracking Data
    Alina Bialkowski, Patrick Lucey, Peter Carr, Yisong Yue, Sridha Sridharan, Iain Matthews
    IEEE International Conference on Data Mining (ICDM), December, 2014.
    [pdf]
  • Personalized Collaborative Clustering
    Yisong Yue, Chong Wang, Khalid El-Arini, Carlos Guestrin
    International World Wide Web Conference (WWW), April, 2014.
    [pdf][slides][data]
  • "Win at Home and Draw Away": Automatic Formation Analysis Highlighting the Differences in Home and Away Team Behaviors
    Alina Bialkowski, Patrick Lucey, Peter Carr, Yisong Yue, Iain Matthews
    MIT Sloan Sports Analytics Conference (SSAC), February, 2014.
    [pdf]
  • "How to Get an Open Shot": Analyzing Team Movement in Basketball using Tracking Data
    Patrick Lucey, Alina Bialkowski, Peter Carr, Yisong Yue, Iain Matthews
    MIT Sloan Sports Analytics Conference (SSAC), February, 2014.
    [pdf]
  • Adaptive Collective Routing Using Gaussian Process Dynamic Congestion Models
    Siyuan Liu, Yisong Yue, Ramayya Krishnan
    ACM Conference on Knowledge Discovery and Data Mining (KDD), August, 2013.
    [pdf]
  • Knapsack Constrained Contextual Submodular List Prediction with Application to Multi-document Summarization
    Jiaji Zhou, Stephane Ross, Yisong Yue, Debadeepta Dey, J. Andrew Bagnell
    ICML Workshop on Inferning: Interactions between Inference and Learning, June, 2013.
    [pdf][software]
  • Learning Policies for Contextual Submodular Prediction
    Stephane Ross, Jiaji Zhou, Yisong Yue, Debadeepta Dey, J. Andrew Bagnell
    International Conference on Machine Learning (ICML), June, 2013.
    [pdf][long][software][video]
  • An Efficient Simulation-based Approach to Ambulance Fleet Allocation and Dynamic Redeployment
    Yisong Yue, Lavanya Marla, Ramayya Krishnan
    AAAI Conference on Artificial Intelligence (AAAI), Special Track on Computational Sustainability and Artificial Intelligence, July, 2012.
    [pdf][spotlight slide][poster][press release][data]
  • Hierarchical Exploration for Accelerating Contextual Bandits
    Yisong Yue, Sue Ann Hong, Carlos Guestrin
    International Conference on Machine Learning (ICML), June, 2012.
    [pdf][long][slides][poster][video]
  • The K-armed Dueling Bandits Problem
    Yisong Yue, Josef Broder, Robert Kleinberg, Thorsten Joachims
    Journal of Computer and System Sciences (JCSS), Special Issue on Learning Theory, DOI:10.1016/j.jcss.2011.12.028, May, 2012.
    [pdf][online]
  • Large-Scale Validation and Analysis of Interleaved Search Evaluation
    Olivier Chapelle, Thorsten Joachims, Filip Radlinski, Yisong Yue
    ACM Transactions on Information Systems (TOIS), 30(1), 6:1--6:41, February, 2012.
    (Selected for ACM Notable Computing Books and Articles of 2012)
    [pdf]
  • Linear Submodular Bandits and their Application to Diversified Retrieval
    Yisong Yue, Carlos Guestrin
    Neural Information Processing Systems (NIPS), December, 2011.
    [pdf][long][poster]
  • Beat the Mean Bandit
    Yisong Yue, Thorsten Joachims
    International Conference on Machine Learning (ICML), June, 2011.
    [pdf][slides][poster][video]
  • Dynamic Ranked Retrieval
    Christina Brandt, Thorsten Joachims, Yisong Yue, Jacob Bank
    ACM Conference on Web Search and Data Mining (WSDM), February, 2011.
    (Best Paper Nomination)
    [pdf][software][video]
  • New Learning Frameworks for Information Retrieval
    Yisong Yue
    Ph.D. Dissertation, Cornell University, January, 2011.
    [pdf]
  • Multi-level Structured Models for Document-level Sentiment Classification
    Ainur Yessenalina, Yisong Yue, Claire Cardie
    Conference on Empirical Methods in Natural Language Processing (EMNLP), October, 2010.
    [pdf][software][data]
  • Learning More Powerful Test Statistics for Click-Based Retrieval Evaluation
    Yisong Yue, Yue Gao, Olivier Chapelle, Ya Zhang, Thorsten Joachims
    ACM Conference on Information Retrieval (SIGIR), July, 2010.
    [pdf][slides]
  • Beyond Position Bias: Examining Result Attractiveness as a Source of Presentation Bias in Clickthrough Data
    Yisong Yue, Rajan Patel, Hein Roehrig
    International World Wide Web Conference (WWW), April, 2010.
    [pdf][slides]
  • Predicting Structured Objects with Support Vector Machines
    Thorsten Joachims, Thomas Hofmann, Yisong Yue, Chun-Nam Yu
    Communications of the ACM (CACM), Research Highlight, 52(11), 97--104, November, 2009.
    (With a technical perspective by John Shawe-Taylor.)
    [pdf][online]
  • The K-armed Dueling Bandits Problem
    Yisong Yue, Josef Broder, Robert Kleinberg, Thorsten Joachims
    Conference on Learning Theory (COLT), June, 2009.
    [pdf][slides]
  • Interactively Optimizing Information Retrieval Systems as a Dueling Bandits Problem
    Yisong Yue, Thorsten Joachims
    International Conference on Machine Learning (ICML), June, 2009.
    [pdf][slides][video]
  • Predicting Diverse Subsets Using Structural SVMs
    Yisong Yue, Thorsten Joachims
    International Conference on Machine Learning (ICML), June, 2008.
    [pdf][slides][software][video]
  • On Using Simultaneous Perturbation Stochastic Approximation for IR Measures, and the Empirical Optimality of LambdaRank
    Yisong Yue, Christopher Burges
    NIPS Machine Learning for Web Search Workshop, December, 2007.
    [pdf][tech report]
  • A Support Vector Method for Optimizing Average Precision
    Yisong Yue, Thomas Finley, Filip Radlinski, Thorsten Joachims
    ACM Conference on Information Retrieval (SIGIR), July, 2007.
    [pdf][slides][software]
Tutorials
  • Imitation Learning, co-taught with Hoang Le, presented at ICML 2018.
    [link]
  • 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
  • New Frontiers in Imitation Learning, Rice University, September, 2018.
    [slides]
  • Machine Teaching for Human Learners, IJCAI 2018 Workshop on Humanizing AI, July, 2018.
    [slides]
  • Inference + Imitation, ICML 2018 Workshop on Tractable Probabilistic Models, July, 2018.
    [slides]
  • The Dueling Bandits Problem, Massachusetts Institute of Technology, September, 2017.
    [slides]
  • Learning to Optimize for Structured Output Spaces, University of California Santa Barbara, April, 2017.
    [slides]
  • Recent Applications of Latent Factor Models, Second Spectrum, September, 2015.
    [slides]
  • Learning Spatial Models of Basketball Gameplay, KDD 2015 Workshop on Large-Scale Sports Analytics, August, 2015.
    [slides]
  • Balancing the Explore/Exploit Tradeoff in Interactive Structured Prediction, Cornell University, December, 2014.
    [slides][video]
  • 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]
[All Content © 2018 Yisong Yue]