Indraneel Mukherjee will present his research seminar/general exam on Friday May 16 at 2PM in Room 402. The members of his committee are: Rob Schapire (advisor), David Blei, and Ken Steiglitz. Everyone is invited to attend his talk, and those faculty wishing to remain for the oral exam following are welcome to do so. His abstract and reading list follow below. ---------------------------------------- Abstract: ========= We consider the problem of learning to predict as well as the best in a group of experts making continuous predictions. We assume the learning algorithm has prior knowledge of the maximum number of mistakes of the best expert. We propose a new master strategy that achieves the best known performance for online learning with continuous experts in the mistake bounded model. Our ideas are based on drifting games, a generalization of boosting and online learning algorithms. We also prove new lower bounds based on the drifting games framework which, though not as tight as previous bounds, have simpler proofs and do not require an enormous number of experts. Papers: ======= 1. Yoav Freund and Manfred Opper. Drifting games and Brownian motion. Journal of Computer and System Sciences, 64:113--132, 2002. A preliminary version appeared in the Proceedings of the 13th Annual Conference on Computational Learning Theory, 2000. 2. Yoav Freund. An adaptive version of the boost by majority algorithm. Machine Learning, 43(3):293--318, June 2001. A preliminary version appeared in the Proceedings of the 12th Annual Conference on Computational Learning Theory, 1999. 3. Yoav Freund. Boosting a weak learning algorithm by majority. Information and Computation, 121(2):256--285, 1995. Preliminary versions appeared in the Proceedings of the Third Annual Workshop on Computational Learning Theory, 1990, and in the Proceedings of the Fifth Annual ACM Workshop on Computational Learning Theory, 1992. 4. Robert E. Schapire. Drifting games. Machine Learning, 43(3):265-291, 2001. 5. N. Cesa-Bianchi, Y. Freund, D.P. Helmbold, D. Haussler, R. Schapire, and M.K. Warmuth How to use expert advice Journal of the ACM, 44(3):427-485, 1997. 6. N. Cesa-Bianchi, Y. Freund, D.P. Helmbold, and M.K. Warmuth On-line prediction and conversion strategies Machine Learning, 25:71-110, 1996. 7. J. Abernethy, J. Langford, M. Warmuth Continuous Experts and the Binning Algorithm COLT 2006 8. Nick Littlestone and Manfred K. Warmuth The weighted majority algorithm. Information and Computation, 108:212-261, 1994. 9. Joel Spencer Ulam's searching game with a fixed number of lies. Theoretical Computer Science, 95(2):307-321, 1992 10. David Blackwell An analog of the minmax theorem for vector payoffs. Pacific J. Math. Volume 6, Number 1 (1956), 1-8. Books: ====== 1. Stuart Russell, Peter Norvig. Artificial Intelligence: A modern approach. Chapters: 3.1-3.5 4.1-4.3 6 7.1-7.6 11.1-11.5 8.1-8.3 13.1-13.6 14.1-14.5 15.1-15.6 16.1-16.3 17.1-17.4 18.1-18.5 20.1-20.3,20.5-20.6 21.1-21.4 26 2. Luc Devroye, Laszlo Gyorfi, Gabor Lugosi A Probabilistic Theory of Pattern Recognition Chapters: 2,4,6.1,6.2,6.7,6.8 7,8,12,13,14,15,16, 28, 29, 30 3. Nicolo Cesa Bianchi, Gabor Lugosi Prediction Learning and Games Chapters: 2,3, 4.1-4.3, 6.1-6.3,6.7-6.9, 7.1-7.3, 7.7 - 7.8, 8, 9.1-9.5, 9.8 - 9.11, all of 10 except 10.6, 11.1 - 11.5