Can Entropic Regularization Be Replaced by Squared Euclidean Distance Plus Additional Linear Constraints
There are two main families of on-line algorithms depending on whether a relative entropy or a squared Euclidean distance is used as a regularizer. The difference between the two families can be dramatic. The question is whether one can always achieve comparable performance by replacing the relative entropy regularization by the squared Euclidean distance plus additional linear constraints. We formulate a simple open problem along these lines for the case of learning disjunctions.
KeywordsEuclidean Distance Weight Vector Relative Entropy Neural Information Processing System Perceptron Algorithm
- [KRS01]Khardon, R., Roth, D., Servedio, R.: Efficiency versus convergence of Boolean kernels for on-line learning algorithms. In: Advances in Neural Information Processing Systems 14, pp. 423–430. MIT Press, Cambridge (2001)Google Scholar
- [Lit88]Littlestone, N.: Learning when irrelevant attributes abound: A new linear-threshold algorithm. Machine Learning 2, 285–318 (1988)Google Scholar
- [LW04]Long, P.M., Wu, X.: Mistake bounds for maximum entropy discrimination. In: Advances in Neural Information Processing Systems, vol. 17, MIT Press, Cambridge (December 2004)Google Scholar