Online Learning Meets Optimization in the Dual

We describe a novel framework for the design and analysis of online learning algorithms based on the notion of duality in constrained optimization. We cast a sub-family of universal online bounds as an optimization problem. Using the weak duality theorem we reduce the process of online learning to the task of incrementally increasing the dual objective function. The amount by which the dual increases serves as a new and natural notion of progress. We are thus able to tie the primal objective value and the number of prediction mistakes using and the increase in the dual. The end result is a general framework for designing and analyzing old and new online learning algorithms in the mistake bound model.

[1]  F ROSENBLATT,et al.  The perceptron: a probabilistic model for information storage and organization in the brain. , 1958, Psychological review.

[2]  丸山 徹.  Convex Analysisの二,三の進展について , 1977 .

[3]  N. Littlestone.  Learning Quickly When Irrelevant Attributes Abound: A New Linear-Threshold Algorithm , 1987, 28th Annual Symposium on Foundations of Computer Science (sfcs 1987).

[4]  N. Littlestone.  Mistake bounds and logarithmic linear-threshold learning algorithms , 1990 .

[5]  Dale Schuurmans,et al.  General Convergence Results for Linear Discriminant Updates , 1997, COLT '97.

[6]  Manfred K. Warmuth,et al.  Exponentiated Gradient Versus Gradient Descent for Linear Predictors , 1997, Inf. Comput..

[7]  Claudio Gentile,et al.  The Robustness of the p-Norm Algorithms , 1999, COLT '99.

[8]  Nello Cristianini,et al.  An introduction to Support Vector Machines , 2000 .

[9]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

[10]  Koby Crammer,et al.  Online Passive-Aggressive Algorithms , 2003, J. Mach. Learn. Res..

[11]  Alexander J. Smola,et al.  Online learning with kernels , 2001, IEEE Transactions on Signal Processing.

[12]  Manfred K. Warmuth,et al.  Relative Loss Bounds for Multidimensional Regression Problems , 1997, Machine Learning.

[13]  Yi Li,et al.  The Relaxed Online Maximum Margin Algorithm , 1999, Machine Learning.

[14]  Manfred K. Warmuth,et al.  Relative Loss Bounds for On-Line Density Estimation with the Exponential Family of Distributions , 1999, Machine Learning.

[15]  Claudio Gentile,et al.  On the generalization ability of on-line learning algorithms , 2001, IEEE Transactions on Information Theory.

[16]  Yoram Singer,et al.  The Forgetron: A Kernel-Based Perceptron on a Fixed Budget , 2005, NIPS.

[17]  Stephen P. Boyd,et al.  Convex Optimization , 2004, Algorithms and Theory of Computation Handbook.