Peter Bartlett
Research Areas
- Artificial Intelligence (AI), machine learning, statistical learning theory
- Control, Intelligent Systems, and Robotics (CIR)
Research Centers
- Berkeley Artificial Intelligence Research Lab (BAIR)
- Berkeley Deep Drive (BDD)
- Center for the Theoretical Foundations of Learning, Inference, Information, Intelligence, Mathematics and Microeconomics at Berkeley (CLIMB)
- CITRIS People and Robots (CPAR)
- Simons Institute for the Theory of Computing (SITC)
Biography
Peter Bartlett is a professor in the Department of Electrical Engineering and Computer Sciences and the Department of Statistics and Head of Google Research Australia. Since 2020, he has been Director of the Foundations of Data Science Institute and Director of the Collaboration on the Theoretical Foundations of Deep Learning. His research interests include machine learning and statistical learning theory. He is the co-author of the book Neural Network Learning: Theoretical Foundations. He has served as an associate editor of the journals Bernoulli, Mathematics of Operations Research, the Journal of Artificial Intelligence Research, the Journal of Machine Learning Research, the IEEE Transactions on Information Theory, Machine Learning, and Mathematics of Control Signals and Systems, and as program committee co-chair for COLT and NeurIPS. He has served as the Associate Director of the Simons Institute for the Theory of Computing and has been a Professor in Mathematical Sciences at the Queensland University of Technology, a Miller Institute Visiting Research Professor in Statistics and Computer Science at U.C. Berkeley, a fellow, senior fellow, and professor in the Research School of Information Sciences and Engineering at the Australian National University's Institute for Advanced Studies, an honorary professor at the University of Queensland and a visiting professor at the University of Paris. He was awarded the Malcolm McIntosh Prize for Physical Scientist of the Year in 2001, and was chosen as an Institute of Mathematical Statistics Medallion Lecturer in 2008, an IMS Fellow and Australian Laureate Fellow in 2011, and a Fellow of the ACM in 2018. He was elected to the Australian Academy of Science in 2015.
Education
- 1992, Ph.D., Electrical Engineering, University of Queensland, Australia
Selected Publications
- W. Mou, M. Yi-An, M. Wainwright, P. Bartlett, and M. Jordan, "High-order Langevin diffusion yields an accelerated MCMC algorithm," Journal of Machine Learning Research, vol. 22, pp. 1-48, March 2021.
- 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.
- 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.
- 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.
- 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.
- 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.
- P. Bartlett and M. Traskin, "AdaBoost is consistent," J. Machine Learning Research, vol. 8, no. 10, pp. 2347-2368, Oct. 2007.
- 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.
- 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.
- 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.
- 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.
- J. Baxter and P. Bartlett, "Infinite-horizon policy-gradient estimation," J. Artificial Intelligence Research, vol. 15, pp. 319-350, Nov. 2001.
- M. Anthony and P. L. Bartlett, Neural Network Learning: Theoretical Foundations, Cambridge; New York: Cambridge University Press, 1999.
