COLT '90 Proceedings of the third annual workshop on Computational learning theory
The perception: a probabilistic model for information storage and organization in the brain
Neurocomputing: foundations of research
Redundant noisy attributes, attribute errors, and linear-threshold learning using winnow
COLT '91 Proceedings of the fourth annual workshop on Computational learning theory
On-line learning of rectangles in noisy environments
COLT '93 Proceedings of the sixth annual conference on Computational learning theory
The weighted majority algorithm
Information and Computation
On-line prediction and conversion strategies
Machine Learning
Exponentiated gradient versus gradient descent for linear predictors
Information and Computation
Predicting Nearly As Well As the Best Pruning of a Decision Tree
Machine Learning - Special issue on the eighth annual conference on computational learning theory, (COLT '95)
Journal of the ACM (JACM)
Artificial Intelligence - Special issue on relevance
Efficient learning with virtual threshold gates
Information and Computation
Machine Learning - Special issue on context sensitivity and concept drift
Neural Networks: A Comprehensive Foundation
Neural Networks: A Comprehensive Foundation
FOCS '95 Proceedings of the 36th Annual Symposium on Foundations of Computer Science
COLT' 98 Proceedings of the eleventh annual conference on Computational learning theory
Machine Learning - Special issue on context sensitivity and concept drift
The robustness of the p-norm algorithms
COLT '99 Proceedings of the twelfth annual conference on Computational learning theory
Direct and indirect algorithms for on-line learning of disjunctions
Theoretical Computer Science
Evidence that Incremental Delta-Bar-Delta Is an Attribute-Efficient Linear Learner
ECML '02 Proceedings of the 13th European Conference on Machine Learning
Direct and Indirect Algorithms for On-line Learning of Disjunctions
EuroCOLT '99 Proceedings of the 4th European Conference on Computational Learning Theory
Large Margin Classification for Moving Targets
ALT '02 Proceedings of the 13th International Conference on Algorithmic Learning Theory
Tracking a Small Set of Experts by Mixing Past Posteriors
COLT '01/EuroCOLT '01 Proceedings of the 14th Annual Conference on Computational Learning Theory and and 5th European Conference on Computational Learning Theory
Learning Additive Models Online with Fast Evaluating Kernels
COLT '01/EuroCOLT '01 Proceedings of the 14th Annual Conference on Computational Learning Theory and and 5th European Conference on Computational Learning Theory
A Second-Order Perceptron Algorithm
COLT '02 Proceedings of the 15th Annual Conference on Computational Learning Theory
Tracking Linear-Threshold Concepts with Winnow
COLT '02 Proceedings of the 15th Annual Conference on Computational Learning Theory
Tracking the best linear predictor
The Journal of Machine Learning Research
Tracking a small set of experts by mixing past posteriors
The Journal of Machine Learning Research
Using confidence bounds for exploitation-exploration trade-offs
The Journal of Machine Learning Research
The Robustness of the p-Norm Algorithms
Machine Learning
Tracking linear-threshold concepts with Winnow
The Journal of Machine Learning Research
Proceedings of the 24th international conference on Machine learning
Tracking the best hyperplane with a simple budget Perceptron
Machine Learning
Machine learning: a review of classification and combining techniques
Artificial Intelligence Review
Projective DNF formulae and their revision
Discrete Applied Mathematics
Dynamic Weighted Majority: An Ensemble Method for Drifting Concepts
The Journal of Machine Learning Research
Online Rule Learning via Weighted Model Counting
Proceedings of the 2008 conference on ECAI 2008: 18th European Conference on Artificial Intelligence
An incremental ensemble of classifiers
Artificial Intelligence Review
Tracking the best hyperplane with a simple budget perceptron
COLT'06 Proceedings of the 19th annual conference on Learning Theory
Tracking the best of many experts
COLT'05 Proceedings of the 18th annual conference on Learning Theory
Online Learning and Online Convex Optimization
Foundations and Trends® in Machine Learning
Hi-index | 0.00 |
Littlestone developed a simple deterministic on-line learning algorithm for learning k-literal disjunctions. This algorithm(called {\sc Winnow}) keeps one weight for each of then variables and does multiplicative updates to its weights. Wedevelop a randomized version of {\sc Winnow} and prove boundsfor an adaptation of the algorithm for the case when the disjunction maychange over time. In this case a possible target {\it disjunctionschedule} &Tgr; is a sequence of disjunctions (one per trial) andthe {\it shift size} is the total number of literals that areadded/removed from the disjunctions as one progresses through thesequence.We develop an algorithm that predicts nearly as well as the bestdisjunction schedule for an arbitrary sequence of examples. This algorithmthat allows us to track the predictions of the best disjunction is hardlymore complex than the original version. However, the amortized analysisneeded for obtaining worst-case mistake bounds requires new techniques. Insome cases our lower bounds show that the upper bounds of our algorithm havethe right constant in front of the leading term in the mistake bound andalmost the right constant in front of the second leading term. Computerexperiments support our theoretical findings.