Vitaly Kuznetsov

Courant Institute of Mathematical Sciences
Department of Mathematics

Office: WWH 709
firstname@cims.nyu.edu

Short Bio

I am a Ph.D. candidate in applied mathematics at the Courant Institute of Mathematical Sciences. My advisor is Professor
Mehryar Mohri. Before coming to Courant Institute, I received Bachelor's and Master's degrees in mathematics and computer science from University of Toronto. I have also spent last two summers at Google Research, working on anomaly detection in time series and large-scale language modeling.

Research Interests

My current research interest is machine learning theory with practical impact. Within machine learning, my recent focus is on time series analysis and ensemble methods. More generally, I am interested in probability theory, theoretical computer science and optimization.

Acknowledgments

I thank National Science and Engineering Research Council of Canada for recognizing my work and supporting my research via Alexander Graham Bell Canada Graduate Scholarship. I am also grateful to the Courant Institute for their support via McCracken Fellowship.

Workshops & Seminars

Publications

  1. Vitaly Kuznetsov and Mehryar Mohri.
    Time series prediction and online learning.
    In Proceedings of The 29th Annual Conference on Learning Theory (COLT 2016). New York, USA, June 2016.
  2. Vitaly Kuznetsov and Mehryar Mohri.
    Generalization bounds for non-stationary mixing processes.
    Machine Learning Journal, to appear, 2016.
  3. Corinna Cortes, Prasoon Goyal, Vitaly Kuznetsov and Mehryar Mohri.
    Kernel extraction via voted risk minimization.
    Journal of Machine Learning Research (JMLR), 44:72-89, 2015.
  4. Vitaly Kuznetsov and Mehryar Mohri.
    Learning theory and algorithms for forecasting non-stationary time series.
    In Advances in Neural Information Processing Systems (NIPS 2015). Montreal, Canada, December 2015.
    (full oral, top 15 papers out of 1838 submissions)
  5. Corinna Cortes, Vitaly Kuznetsov, Mehryar Mohri and Manfred Warmuth.
    On-line learning algorithms for path experts with non-additive losses.
    In Proceedings of The 28th Annual Conference on Learning Theory (COLT 2015). Paris, France, July 2015.
  6. Corinna Cortes, Vitaly Kuznetsov, Mehryar Mohri and Umar Syed.
    Structural maximum entropy models.
    In Proceedings of the 32st International Conference on Machine Learning (ICML 2015). Lille, France, July 2015.
  7. Vitaly Kuznetsov, Mehryar Mohri and Umar Syed.
    Multi-class deep boosting.
    In Advances in Neural Information Processing Systems (NIPS 2014). Montreal, Canada, December 2014.
  8. Vitaly Kuznetsov and Mehryar Mohri.
    Generalization bounds for time series prediction with non-stationary processes.
    In Proceedings of the 25th International Conference on Algorithmic Learning Theory (ALT 2014). Bled, Slovenia, October 2014.
  9. Corinna Cortes, Vitaly Kuznetsov and Mehryar Mohri.
    Learning ensembles of structured prediction rules.
    In Proceedings of the 52nd Annual Meeting of Association for Computational Linguistics (ACL 2014). Baltimore, USA, June 2014.
  10. Corinna Cortes, Vitaly Kuznetsov and Mehryar Mohri.
    Ensemble methods for structured prediction.
    In Proceedings of the 31st International Conference on Machine Learning (ICML 2014). Beijing, China, June 2014.
  11. Abraham Isgur, Vitaly Kuznetsov, Mustazee Rahman and Stephen Tanny.
    Nested recursions, simultaneous parameters and tree superpositions.
    Electronic Journal of Combinatorics. Volume 21, Issue 1, 2014.
  12. Abraham Isgur, Vitaly Kuznetsov and Stephen Tanny.
    A combinatorial approach for solving certain nested recursions with non-slow solutions.
    Journal of Difference Equations and Applications, Volume 19, Issue 4, 2013.
  13. Rafal Drabek, Abraham Isgur, Vitaly Kuznetsov and Stephen Tanny.
    Sums of ceiling functions solve nested recursions
    Journal of Difference Equations and Applications, Volume 18, Issue 12, 2012.
  14. Abraham Isgur, Vitaly Kuznetsov and Stephen Tanny.
    Nested recursions with ceiling function solutions
    Journal of Difference Equations and Applications, Volume 18, Issue 6, 2012.

Workshop papers

  1. Vitaly Kuznetsov, Mehryar Mohri and Umar Syed.
    Rademacher complexity margin bounds for learning with a large number of classes.
    In ICML 2015 Workshop on Extreme Classification. Lille, France, July 2015.
  2. Corinna Cortes, Vitaly Kuznetsov and Mehryar Mohri.
    Boosting ensembles of structured prediction rules.
    In NIPS 2014 Workshop on Modern Machine Learning and Natural Language Processing. Montreal, Canada, December 2014.
  3. Corinna Cortes, Vitaly Kuznetsov and Mehryar Mohri.
    On-line learning approach to ensemble methods for structured prediction.
    In NIPS 2014 Workshop on Representation and Learning Methods Complex Outputs. Montreal, Canada, December 2014.
  4. Vitaly Kuznetsov and Mehryar Mohri.
    Forecasting non-stationary time series: from theory to algorithms.
    In NIPS 2014 Workshop on Transfer and Multi-task Learning. Montreal, Canada, December 2014.

Recent talks

  • Learning Theory and Algorithms for Time Series Prediction. NIPS 2015, Montreal, Canada, December 2015. Video
  • Ensemble methods for structured prediction.
    ICML Workshop on Features and Structures 2015, Lille, Frace, July 2015. Slides
  • Rademacher complexity margin bounds for learning with a large number of classes.
    ICML 2015 Workshop on Extreme Classification, Lille, France, July 2015.
  • Structural maximum entropy models. ICML 2015, Lille, Frace, July 2015. Video
  • On-line learning algorithms for path experts with non-additive losses. COLT 2015, Paris, France, July 2015. Video
  • Learning ensembles of structure prediction rules.
    9th Annual Machine Learning Symposium, New York Academy of Science, New York, March 2015.
  • On-line learning approach to ensemble methods for structured prediction.
    NIPS 2014 Workshop on Representation and Learning Methods Complex Outputs, Montreal, Canada, December 2014. Video
  • Generalization bounds for time series prediction with non-stationary processes. ALT 2014, Bled, Slovenia, October 2014.
  • Learning ensembles of structured prediction rules. Google Research, New York, July 2014.
  • Ensemble methods for structured prediction. ICML 2014, Beijing, China, June 2014. Video

Recent teaching