# Faculty Publications - Peter Bartlett

## Books

- A. J. Smola, P. L. Bartlett, B. Schölkopf, and D. Schuurmans, Eds.,
*Advances in Large Margin Classifiers*, Neural Information Processing Series, Cambridge, MA: MIT Press, 2000. [abstract] - M. Anthony and P. L. Bartlett,
*Neural Network Learning: Theoretical Foundations*, Cambridge; New York: Cambridge University Press, 1999. [abstract]

## Book chapters or sections

- J. Abernethy, P. Bartlett, A. Rakhlin, and A. Tewari, "Optimal strategies and minimax lower bounds for online convex games," in
*Learning Theory: Proc. 21st Annual Conf. (COLT 2008)*, R. A. Servedio and T. Zhang, Eds., Lecture Notes in Computer Science, Berlin, Germany: Springer-Verlag, 2008, pp. 415-424. - P. Bartlett, V. Dani, T. P. Hayes, S. Kakade, A. Rakhlin, and A. Tewari, "High-probability regret bounds for bandit online linear optimization," in
*Learning Theory: Proc. 21st Annual Conf. (COLT 2008)*, R. A. Servedio and T. Zhang, Eds., Lecture Notes in Computer Science, Berlin, Germany: Springer-Verlag, 2008, pp. 335-342. - A. Tewari and P. Bartlett, "Optimistic linear programming gives logarithmic regret for irreducible MDPs," in
*Advances in Neural Information Processing Systems 20: Proc. of the 21st Annual Conf. (NIPS 2007)*, D. Koller, Y. Singer, and J. Platt, Eds., Advances in Neural Information Processing Systems, Vol. 20, Cambridge, MA: MIT Press, 2008. [abstract] - P. Bartlett, E. Hazan, and A. Rakhlin, "Adaptive online gradient descent," in
*Advances in Neural Information Processing Systems 20: Proc. of the 21st Annual Conf. (NIPS 2007)*, D. Koller, Y. Singer, and J. Platt, Eds., Advances in Neural Information Processing Systems, Vol. 20, Cambridge, MA: MIT Press, 2008. [abstract] - P. Bartlett and M. Traskin, "AdaBoost is consistent," in
*Advances in Neural Information Processing Systems 19: Proc. of the 20th Annual Conf. (NIPS 2006)*, B. Scholkopf, J. Platt, and T. Hoffman, Eds., Advances in Neural Information Processing, Vol. 19, Cambridge, MA: MIT Press, 2007, pp. 105-112. - B. I. P. Rubinstein, P. Bartlett, and J. H. Rubinstein, "Shifting, one-inclusion mistake bounds and tight multiclass expected risk bounds," in
*Advances in Neural Information Processing Systems 19: Proc. of the 20th Annual Conf. (NIPS 2006)*, B. Scholkopf, J. Platt, and T. Hoffman, Eds., Advances in Neural Information Processing Systems, Vol. 19, Cambridge, MA: MIT Press, 2007, pp. 1193-1200. - P. Bartlett and A. Tewari, "Sample complexity of policy search with known dynamics," in
*Advances in Neural Information Processing Systems 19: Proc. of the 20th Annual Conf. (NIPS 2006)*, B. Scholkopf, J. Platt, and T. Hoffman, Eds., Advances in Neural Information Processing Systems, Vol. 19, Cambridge, MA: MIT Press, 2007, pp. 97-104. - J. Abernethy, P. Bartlett, and A. Rakhlin, "Multitask learning with expert advice," in
*Learning Theory: Proc. 20th Annual Conf. on Learning Theory (COLT 2007)*, N. H. Bshouty and C. Gentile, Eds., Lecture Notes in Computer Science: Artificial Intelligence, Vol. 4539, Berlin, Germany: Springer-Verlag, 2007, pp. 484-498. - A. Tewari and P. Bartlett, "Bounded parameter Markov decision processes with average reward criterion," in
*Learning Theory: Proc. 20th Annual Conf. on Learning Theory (COLT 2007)*, N. H. Bshouty and C. Gentile, Eds., Lecture Notes in Computer Science: Artificial Intelligence, Vol. 4539, Berlin, Germany: Springer-Verlag, 2007, pp. 263-277. - A. Rakhlin, J. Abernethy, and P. Bartlett, "Online discovery of similarity mappings," in
*Proc. 24th Intl. Conf. on Machine Learning (ICML-2007)*, Z. Ghahramani, Ed., ACM International Conference Proceeding Series, Vol. 227, New York, NY: The Association for Computing Machinery, Inc., 2007, pp. 767-774. - P. Bartlett, M. Collins, B. Taskar, and D. McAllester, "Exponentiated gradient algorithms for large-margin structured classification," in
*Advances in Neural Information Processing Systems 17: Proc. of the 18th Annual Conf. (NIPS 2004)*, L. K. Saul, Y. Weiss, and L. Bottou, Eds., Advances in Neural Information Processing Systems, Vol. 17, Cambridge, MA: MIT Press, 2005, pp. 113-120. - A. Tewari and P. Bartlett, "On the consistency of multiclass classification methods," in
*Learning Theory: Proc. of the 18th Annual Conf. on Learning Theory (COLT 2005)*, P. Auer and R. Meir, Eds., Lecture Notes in Computer Science: Artificial Intelligence, Vol. 3559, Berlin, Germany: Springer-Verlag, 2005, pp. 143-157. - P. Bartlett, M. Jordan, and J. D. McAuliffe, "Large margin classifiers: Convex loss, low noise, and convergence rates," in
*Advances in Neural Information Processing Systems 16: Proc. 17th Annual Conf. (NIPS 2003)*, S. Thrun, L. K. Saul, and B. Schoelkopf, Eds., Advances in Neural Information Processing Systems, Vol. 16, Cambridge, MA: MIT Press, 2004, pp. 1173-1180.

## Articles in journals or magazines

- A. Barth, B. I. P. Rubinstein, M. Sundararajan, J. C. Mitchell, D. Song, and P. Bartlett, "A Learning-Based Approach to Reactive Security.,"
*IEEE Transactions on Dependable and Secure Computing*, vol. 9, no. 4, pp. 482-493, July 2012. - W. S. Lee, P. Bartlett, and R. C. Williamson, "Correction to "The Importance of Convexity in Learning with Squared Loss","
*IEEE Trans. Information Theory*, vol. 54, no. 9, pp. 4395-4395, Sep. 2008. - M. Collins, A. Globerson, T. Koo, X. Carreras, and P. Bartlett, "Exponentiated gradient algorithms for conditional random fields and max-margine Markov networks,"
*J. Machine Learning Research*, vol. 9, no. 8, pp. 1775-1822, Aug. 2008. - P. Bartlett and M. H. Wegkamp, "Classification with a reject option using a hinge loss,"
*J. Machine Learning Research*, vol. 9, no. 8, pp. 1823-1840, Aug. 2008. - P. Bartlett and M. Traskin, "AdaBoost is consistent,"
*J. Machine Learning Research*, vol. 8, no. 10, pp. 2347-2368, Oct. 2007. - A. Tewari and P. Bartlett, "On the consistency of multiclass classification methods,"
*J. Machine Learning Research: Special Topic on the Conference on Learning Theory 2005*, vol. 8, no. 5, pp. 1007-1025, May 2007. - P. Bartlett and A. Tewari, "Sparseness vs estimating conditional probabilities: Some asymptotic results,"
*J. Machine Learning Research*, vol. 9, no. 4, pp. 775-790, April 2007. - P. Bartlett and S. Mendelson, "Discussion of "2004 IMS Medallion Lecture: Local Rademacher complexities and oracle inequalities in risk minimization" by V. Koltchinskii","
*The Annals of Statistics*, vol. 34, no. 6, pp. 2657-2663, Dec. 2006. - P. Bartlett, M. Jordan, and J. D. McAuliffe, "Comment on "Support vector machines with applications","
*Statistical Science*, vol. 21, no. 3, pp. 341-346, Aug. 2006. - P. Bartlett and S. Mendelsohn, "Empirical minimization,"
*Probability Theory and Related Fields*, vol. 135, no. 3, pp. 311-334, July 2006. - P. Bartlett, M. Jordan, and J. D. McAuliffe, "Convexity, classification, and risk bounds,"
*J. American Statistical Association*, vol. 101, no. 473, pp. 138-156, March 2006. - P. Bartlett, O. Bousquet, and S. mendelson, "Local Rademacher complexities,"
*The Annals of Statistics*, vol. 33, no. 4, pp. 1497-1537, Aug. 2005. - P. Bartlett, O. Bousquet, and S. Mendelson, "Local Rademacher complexities,"
*The Annals of Statistics*, vol. 33, no. 4, pp. 1497-1537, Aug. 2005. - G. R. G. Lanckriet, N. Cristianini, P. Bartlett, L. El Ghaoui, and M. Jordan, "Learning the kernel matrix with semidefinite programming,"
*J. Machine Learning Research*, vol. 5, pp. 27-72, Dec. 2004. - P. Bartlett, M. Jordan, and J. D. McAuliffe, "[Consistency in Boosting]: Discussion,"
*Annals of Statistics*, vol. 32, no. 1, pp. 85-91, Feb. 2004. - J. Baxter and P. Bartlett, "Infinite-horizon policy-gradient estimation,"
*J. Artificial Intelligence Research*, vol. 15, pp. 319-350, Nov. 2001. - R. E. Schapire, Y. Freund, P. Bartlett, and W. S. Lee, "Boosting the margin: A new explanation for the effectiveness of voting methods,"
*The Annals of Statistics*, vol. 26, no. 5, pp. 1651-1686, May 1998. - P. Bartlett, "The sample complexity of pattern classification with neural networks: The size of the weights is more important than the size of the network,"
*IEEE Trans. Information Theory*, vol. 44, no. 2, pp. 525-536, March 1998.

## Articles in conference proceedings

- F. Hedayati and P. Bartlett, "citeKey, The Optimality of {J}effreys Prior for Online DensityEstimation and the Asymptotic Normality of MaximumLikelihood Estimators," in
*Proceedings of the Conference onLearning Theory (COLT2012)*, Vol. 23, 2012, pp. 7.1-7.13. [abstract] - F. Hedayati and P. Bartlett, "Exchangeability Characterizes Optimality of SequentialNormalized Maximum Likelihood and {Bayesian} Prediction with {Jeffreys}Prior," in
*Proceedings of The Fifteenth International Conference on Artificial Intelligence and Statistics(AISTATS)*, M. Girolami and N. Lawrence, Eds., 2012. [abstract] - F. Hedayati and P. Bartlett, "Exchangeability Characterizes Optimality of SequentialNormalized Maximum Likelihood and Bayesian Prediction with JeffreysPrior," in
*Proceedings of The Fifteenth International Conference on Artificial Intelligence and Statistics(AISTATS)*, M. Girolami and N. Lawrence, Eds., 2012. [abstract] - J. Abernethy, P. Bartlett, N. Buchbinder, and I. Stanton, "A Regularization Approach to Metrical Task Systems," in
*Algorithmic Learning Theory, 21th International Conference, {ALT} 2010, Canberra, Australia, October 6-8, 2010, Proceedings*, M. Hutter, F. Stephan, V. Vovk, and T. Zeugmann, Eds., Lecture Notes in Artificial Intelligence, Vol. 6331, Berlin, Heidelberg, New York: Springer, 2010, pp. 270--284. - A. Barth, B. I. P. Rubinstein, M. Sundararajan, J. C. Mitchell, D. Song, and P. Bartlett, "A Learning-Based Approach to Reactive Security," in
*Financial Cryptography and Data Security '10. Fourteenth International Conference*, 2010. - M. Barreno, P. Bartlett, F. J. Chi, A. D. Joseph, B. Nelson, B. I. P. Rubinstein, U. Saini, and D. Tygar, "Open problems in the security of learning (Position Paper)," in
*Proc. 1st ACM Workshop on AISec (AISec 2008)*, New York, NY: The Association for Computing Machinery, Inc., 2008, pp. 19-26. - D. Rosenberg and P. Bartlett, "The Rademacher complexity of co-regularized kernel classes," in
*Proc. 11th Intl. Conf. on Artificial Intelligence and Statistics (AISTAT 2007)*, M. Meila and X. Shen, Eds., Vol. 2, Cambridge, MA: Journal of Machine Learning Research/MIT, 2007, pp. 396-403. - R. Jimenez-Rodriguez, N. Sitar, and P. Bartlett, "Maximum likelihood estimation of trace length distribution parameters using the EM algorithm," in
*Prediction, Analysis and Design in Geomechanical Applications: Proc. 11th Intl. Conf. of Computer Methods and Advances in Geomechanics (IACMAG)*, G. Barla and M. Barla, Eds., Bologna, Italy: Patron Editore, 2005, pp. 619-626.

## Technical Reports

- M. Kloft, U. Rückert, and P. Bartlett, "A Unifying View of Multiple Kernel Learning," EECS Department, University of California, Berkeley, Tech. Rep. UCB/EECS-2010-49, May 2010. [abstract]
- A. Agarwal, A. Rakhlin, and P. Bartlett, "Matrix regularization techniques for online multitask learning," EECS Department, University of California, Berkeley, Tech. Rep. UCB/EECS-2008-138, Oct. 2008. [abstract]
- J. D. Abernethy, P. Bartlett, A. Rakhlin, and A. Tewari, "Optimal Strategies and Minimax Lower Bounds for Online Convex Games," EECS Department, University of California, Berkeley, Tech. Rep. UCB/EECS-2008-19, Feb. 2008. [abstract]
- A. Rakhlin, A. Tewari, and P. Bartlett, "Closing the Gap between Bandit and Full-Information Online Optimization: High-Probability Regret Bound," EECS Department, University of California, Berkeley, Tech. Rep. UCB/EECS-2007-109, Aug. 2007. [abstract]
- B. I. P. Rubinstein, P. Bartlett, and J. H. Rubinstein, "Shifting: One-Inclusion Mistake Bounds and Sample Compression," EECS Department, University of California, Berkeley, Tech. Rep. UCB/EECS-2007-86, June 2007. [abstract]
- P. Bartlett, E. Hazan, and A. Rakhlin, "Adaptive Online Gradient Descent," EECS Department, University of California, Berkeley, Tech. Rep. UCB/EECS-2007-82, June 2007. [abstract]
- P. Bartlett, "Fast Rates for Estimation Error and Oracle Inequalities for Model Selection," University of California, Department of Statistics, Tech. Rep. UCB/STAT-03-728, March 2007.
- J. D. Abernethy, P. Bartlett, and A. Rakhlin, "Multitask Learning with Expert Advice," EECS Department, University of California, Berkeley, Tech. Rep. UCB/EECS-2007-20, Jan. 2007. [abstract]
- P. Bartlett and M. Traskin, "AdaBoost Is Consistent," University of California, Department of Statistics, Tech. Rep. UCB/STAT-12-722, Dec. 2006.
- P. Bartlett, M. Jordan, and J. D. McAuliffe, "Convexity, Classification, and Risk Bounds," University of California, Department of Statistics, Tech. Rep. UCB/STAT-04-638, April 2003.
- G. R. G. Lanckriet, N. Cristianini, P. Bartlett, L. El Ghaoui, and M. I. Jordan, "Learning the Kernel Matrix with Semi-Definite Programming," EECS Department, University of California, Berkeley, Tech. Rep. UCB/CSD-02-1206, 2002. [abstract]

## Patents

- P. L. Bartlett, A. Elisseeff, and B. Schoelkopf, "Kernels and methods for selecting kernels for use in learning machines," U.S. Patent Application. Nov. 2003.

## Masters Reports

- S. Rao and J. Hong, "Analysis of Hidden Markov Models and Support Vector Machines in Financial Applications," P. Bartlett, Ed., EECS Department, University of California, Berkeley, Tech. Rep. UCB/EECS-2010-63, May 2010. [abstract]