Robert Schapire

Home * People * Robert Schapire

Robert Schapire

Robert E. Schapire,
an American mathematician, computer scientist, professor at Princeton University, and since 2014 principal researcher at Microsoft Research . He received his Bachelor degree in mathematics and CS from Brown University in 1986, and his Masters degree and Ph.D. from MIT in 1988 and 1991 respectively, both under the supervision of Ronald L. Rivest . His research interest is in theoretical and applied machine learning, with particular focus on computational statistics, boosting, online learning, game theory, and maximum entropy. On his work in collaboration with Yoav Freund on AdaBoost, an ensemble learning algorithm which is used to combine many "weak" learning machines to create a more robust one, he received the 2003 Gödel prize in theoretical computer science, and the Paris Kanellakis Award in 2004. Further, along with Peter Auer and Nicolò Cesa-Bianchi, Yoav Freund and Robert Schapire worked on multi-armed bandit problems .

Selected Publications

1987 ...

• Ronald L. Rivest, Robert Schapire (1987). Diversity-Based Inference of Finite Automata. (Extended Abstract) FOCS 1987, pdf
• Ronald L. Rivest, Robert Schapire (1989). Inference of Finite Automata Using Homing Sequences. (Extended Abstract) STOC 1989, pdf
• Robert Schapire (1989). The Strength of Weak Learnability. (Extended Abstract) FOCS 1989

1990 ...

• Ronald L. Rivest, Robert Schapire (1990). A new approach to unsupervised learning in deterministic environments. Machine learning: an artificial intelligence approach volume III, pdf preprint
• Robert Schapire (1990). The Strength of Weak Learnability. Machine Learning, Vol. 5, pdf
• David Haussler, Michael Kearns, Manfred Opper, Robert Schapire (1991). Estimating Average-Case Learning Curves Using Bayesian, Statistical Physics and VC Dimension Methods. NIPS 1991
• Robert Schapire (1991). The Design and Analysis of Efficient Learning Algorithms. Ph.D. thesis, MIT, supervisor Ronald L. Rivest, pdf
• Robert Schapire (1992). The Design and Analysis of Efficient Learning Algorithms. MIT Press, (ACM Doctoral Dissertation Award), amazon
• Ronald L. Rivest, Robert Schapire (1994). Diversity-Based Inference of Finite Automata. Journal of the ACM, Vol. 41, No. 3, pdf

1995 ...

• Yoav Freund, Robert Schapire (1996). Game Theory, On-line Prediction and Boosting. COLT 1996, pdf
• Robert Schapire, Manfred K. Warmuth (1996). On the Worst-Case Analysis of Temporal-Difference Learning Algorithms. Machine Learning, Vol. 22, Nos. 1-3, pdf
• Yoav Freund, Robert Schapire (1997). A decision-theoretic generalization of on-line learning and an application to boosting. Journal of Computer and System Sciences, Vol. 55, No. 1, 1996 pdf » AdaBoost
• Nicolò Cesa-Bianchi, Yoav Freund, David P. Helmbold, David Haussler, Robert Schapire, Manfred K. Warmuth (1997). How to Use Expert Advice. Journal of the ACM, Vol. 44, No. 3, pdf
• Peter Auer, Nicolò Cesa-Bianchi, Yoav Freund, Robert Schapire (1998). Gambling in a rigged casino: The adversarial multi-arm bandit problem. NeuroCOLT2, pdf
• Robert Schapire, Yoav Freund, Peter Bartlett, Wee Sun Lee (1998). Boosting the margin: A new explanation for the effectiveness of voting methods. Annals of Statistic, pdf
• Yoav Freund, Robert Schapire (1999). Adaptive game playing using multiplicative weights. Games and Economic Behavior, Vol. 29, pdf
• Robert Schapire (1999). A Brief Introduction to Boosting. IJCAI 1999, pdf
• Robert Schapire (1999). Theoretical Views of Boosting and Applications. ALT 1999, pdf
• Robert Schapire (1999). Drifting Games. COLT 1999, CiteSeerX
• Yoav Freund, Robert Schapire (1999). Large Margin Classification using the Perception Algorithm. Machine Learning, Vol. 37, No. 3, pdf

2000 ...

• David McAllester, Robert Schapire (2000). On the Convergence Rate of Good-Turing Estimators. COLT 2000, CiteSeerX
• Robert Schapire (2002). Advances in Boosting. UAI 2002, arXiv:1301.0599
• Peter Auer, Nicolò Cesa-Bianchi, Yoav Freund, Robert Schapire (2002). The Nonstochastic Multiarmed Bandit Problem. SIAM Journal on Computing, Vol. 32, No. 1, 2001 pdf
• Peter Stone, Robert Schapire, Michael L. Littman, János A. Csirik, David McAllester (2003). Decision-Theoretic Bidding Based on Learned Density Models in Simultaneous, Interacting Auctions. JAIR, Vol. 19
• Robert Schapire (2003). The Boosting Approach to Machine Learning: An Overview. Nonlinear Estimation and Classification, Lecture Notes in Statistics, Vol. 171, Springer, 2002 pdf
• Cynthia Rudin, Ingrid Daubechies, Robert Schapire (2004). The Dynamics of AdaBoost: Cyclic Behavior and Convergence of Margins. Journal of Machine Learning Research, Vol. 5, pdf

2005 ...

• Cynthia Rudin, Robert Schapire, Ingrid Daubechies (2007). Analysis of boosting algorithms using the smooth margin function. Annals of Statistics, Vol. 35, No. 6, arXiv:0803.4092
• Umar Syed, Robert Schapire (2007). A Game-Theoretic Approach to Apprenticeship Learning. NIPS 2007, pdf
• Umar Syed, Michael Bowling, Robert Schapire (2008). Apprenticeship learning using linear programming. ICML 2008, pdf
• Indraneel Mukherjee, Robert Schapire (2008). Learning with Continuous Experts Using Drifting Games. ALT 2008, pdf
• Cynthia Rudin, Robert Schapire (2009). Margin-based Ranking and an Equivalence between AdaBoost and RankBoost. Journal of Machine Learning Research, Vol. 10, pdf

2010 ...

• Robert Schapire (2010). The Convergence Rate of AdaBoost. COLT 2010, pdf
• Indraneel Mukherjee, Cynthia Rudin, Robert Schapire (2011). The Rate of Convergence of AdaBoost. arXiv:1106.6024
• Robert Schapire, Yoav Freund (2012). Boosting: Foundations and Algorithms. MIT Press
• Indraneel Mukherjee, Robert Schapire (2013). A Theory of Multiclass Boosting. Journal of Machine Learning Research, Vol. 14, pdf
• Haipeng Luo, Robert Schapire (2013). Towards Minimax Online Learning with Unknown Time Horizon. arXiv:1307.8187
• Haipeng Luo, Robert Schapire (2014). A Drifting-Games Analysis for Online Learning and Applications to Boosting. arXiv:1406.1856

2015 ...

• Vasilis Syrgkanis, Alekh Agarwal, Haipeng Luo, Robert Schapire (2015). Fast Convergence of Regularized Learning in Games. arXiv:1507.00407
• Furong Huang, Jordan T. Ash, John Langford, Robert Schapire (2017). Learning Deep ResNet Blocks Sequentially using Boosting Theory. arXiv:1706.04964

External Links

• Robert Schapire - Microsoft Research
• Robert Schapire from Wikipedia
• Robert Schapire - Google Scholar Citations
• The Mathematics Genealogy Project - Robert Schapire
• Robert Schapire on Multiclass Boosting, Partha Niyogi Memorial Conference, University of Chicago , December 4, 2011, YouTube Video

References

Up one Level