MACHINE LEARNING THEORY

Text: An Introduction to Computational Learning Theory by Michael Kearns and Umesh Vazirani, plus papers and notes for topics not in the book.

Office hours:MW 4:30-5:15

Handouts

• [Online learning survey] [Winnow paper] [Handout on tail inequalities]
• Homework 1. solutions.
• Homework 2. solutions.
• Homework 3. solutions.
• Homework 4. solutions.
• Homework 5. solutions.
• Homework 6. solutions.

Lecture Notes & tentative plan

1. 01/12: Introduction. PAC model and Occam's razor.
2. 01/14: The Mistake-Bound model. Combining expert advice. Connections to info theory and game theory.
3. 01/21: The Winnow algorithm.
4. 01/26: The Perceptron Algorithm, Margins, and Kernel functions.
5. 01/28: Uniform convergence, tail inequalities (Chernoff/Hoeffding), VC-dimension I. [more notes]
6. 02/02: VC-dimension II.
7. 02/04: Rademacher bounds and McDiarmid's inequality.
8. 02/09: Boosting I: weak vs strong learning, basic issues.
9. 02/11: Boosting II: Adaboost + connection to WM analysis + L_1 margin bounds.
10. 02/16: Support Vector Machines, properties of kernels, MB=>PAC, L_2 margin bounds.
11. 02/18: Margins, kernels, and general similarity functions (L_1 and L_2 connection).
12. 02/23: Cryptographic hardness results.
13. 02/25: Maxent and maximum-likelihood exponential models. Connection to winnow.
14. 03/02: Statistical Query model I.
15. 03/04: Statistical Query model II.
16. 03/16: Fourier-based algorithms.
17. 03/18: Membership Query algorithms.
18. 03/23: Membership Query algorithms II.
19. 03/25: Learning finite-state environments.
20. 03/30: Learning finite-state environments II.
21. 04/01: MDPs and reinforcement learning.
22. 04/06: Offline->online optimization.
23. 04/08: Bandit problems.
24. 04/13: Active learning [Steve Hanneke]
25. 04/15: [class cancelled today]
26. 04/20: online learning and game theory.
27. 04/22: Semi-supervised learning.
28. 04/27: Project presentations
29. 04/29: Project presentations

Additional Readings & More Information

Books and tutorials:

• O. Bousquet, S. Boucheron, and G. Lugosi, Introduction to Statistical Learning Theory.
• PASCAL video lectures.
• N. Cristianini and J. Shawe-Taylor, Kernel Methods for Pattern Analysis, 2004.
• N. Cristianini and J. Shawe-Taylor, An Introduction to Support Vector Machines (and other kernel-based learning methods), 2000.
• M. Anthony and P. Bartlett. Learning in Neural Networks : Theoretical Foundations. Cambridge University Press, 1999.
• V. Vapnik. Statistical Learning Theory. Wiley, 1998.
• L. Devroye, L. Györfi, G. Lugosi, A Probabilistic Theory of Pattern Recognition, Springer, New York, 1996.
• My FOCS'03 tutorial on Machine Learning Theory

Online Learning:

• Nick Littlestone, Learning Quickly when Irrelevant Attributes Abound: A New Linear-threshold Algorithm. Machine Learning 2:285--318, 1987. (The version pointed to here is the tech report UCSC-CRL-87-28.) This is the paper that first defined the Mistake-bound model, and also introduced the Winnow algorithm. A great paper.

• Littlestone and Warmuth, The Weighted Majority Algorithm. Information and Computation 108(2):212-261, 1994. Introduces the weighted majority algorithm, along with a number of variants. Also a great paper.

• Nicolo Cesa-Bianchi, Yoav Freund, David Haussler, David Helmbold, Robert Schapire, and Manfred Warmuth, How to use expert advice, Journal of the ACM, 44(3):427-485, May 1997. Yoav Freund and Robert Schapire, Adaptive game playing using multiplicative weights, Games and Economic Behavior, 29:79-103, 1999. Continuing on with line of research in the [LW] paper, these give tighter analyses of multiplicative-weighting expert algorithms and give a game-theoretic perspective, as well as address a number of other issues.

• Adam Kalai and Santosh Vempala, Efficient algorithms for the online decision problem, COLT '03. Martin Zinkevich, Online convex programming and generalized infinitesimal gradient ascent, ICML '03. These papers give efficient algorithms for a broad class of settings that one can view as having exponentially many "experts", but which are represented in an implicit compact way.

• Peter Auer, Nicolo Cesa-Bianchi, Yoav Freund, Robert Schapire: The Nonstochastic Multiarmed Bandit Problem, SIAM J. Comput. 32(1): 48-77 (2002). Brendan McMahan and Avrim Blum: Online Geometric Optimization in the Bandit Setting Against an Adaptive Adversary, COLT '04. Abie Flaxman, Adam Tauman Kalai, and Brendan McMahan: Online Convex Optimization in the Bandit Setting: Gradient Descent Without a Gradient, SODA '2005. These papers extend above results to the bandit setting, in which only the loss or gain of the action actually played can be observed at each time step.

• Survey articles: Avrim Blum, On-Line Algorithms in Machine Learning. From "Online Algorithms: the state of the art", Fiat and Woeginger eds., LNCS #1442, 1998. Avrim Blum and Yishay Mansour, Learning, Regret Minimization, and Equilibria, Chapter 4 in "Algorithmic Game Theory," Noam Nisan, Tim Roughgarden, Eva Tardos, and Vijay Vazirani, eds. (2007).

• David Haussler Chapter on PAC learning model, and decision-theoretic generalizations, with applications to neural nets. From Mathematical Perspectives on Neural Networks, Lawrence Erlbaum Associates, 1995, containing reprinted material from "Decision Theoretic Generalizations of the PAC Model for Neural Net and Other Learning Applications", Information and Computation, Vol. 100, September, 1992, pp. 78-150. This is a really nice survey of the PAC model and various sample-complexity results.

• David Williamson, John Shawe-Taylor, Bernhard Schölkopf, Alex Smola Sample Based Generalization Bounds. Gives tighter generalization bounds where instead of using "the maximum number of ways of labeling a set of 2m points" you can use "the number of ways of labeling your actual sample".

• The original paper: Robert E. Schapire, The strength of weak learnability. Machine Learning, 5(2):197-227, 1990.
• The Adaboost paper: Yoav Freund and Rob Schapire, A decision-theoretic generalization of on-line learning and an application to boosting, Journal of Computer and System Sciences, 55(1):119-139, 1997.
• An overview by Rob Schapire: The boosting approach to machine learning: An overview. In MSRI Workshop on Nonlinear Estimation and Classification, 2002.

More on Kernels:

• Nati Srebro and Shai Ben-David, Learning Bounds for Support Vector Machines with Learned Kernels, COLT 2006.

Fourier analysis, weak learning, SQ learning:

• Avrim Blum, Merrick Furst, Jeffrey Jackson, Michael Kearns, Yishay Mansour, and Steven Rudich, Weakly Learning DNF and Characterizing Statistical Query Learning Using Fourier Analysis, STOC '94 pp. 253--262.

• Y. Mansour. Learning Boolean Functions via the Fourier Transform. Survey article in ``Theoretical Advances in Neural Computation and Learning", 391--424 (1994).

• A. Blum, C. Burch, and J. Langford, On Learning Monotone Boolean Functions. Proceedings of the 39th Annual Symposium on Foundations of Computer Science (FOCS '98).

• V. Feldman, P. Gopalan, S. Khot, A. Ponnuswami. New Results for Learning Noisy Parities and Halfspaces, FOCS 2006.

Computational hardness results:

• Feldman, Optimal Hardness Results for Maximizing Agreements with Monomials, CCC 2006.
• Kharitonov, Cryptographic hardness of distribution-specific learning, STOC 93.

• Adam Berger's maxent page
• Adwait Ratnaparkhi's statistical NLP page