Mistake bounds and logarithmic linear-threshold learning algorithms
Mistake bounds and logarithmic linear-threshold learning algorithms
Exponentiated gradient versus gradient descent for linear predictors
Information and Computation
Linear hinge loss and average margin
Proceedings of the 1998 conference on Advances in neural information processing systems II
General Convergence Results for Linear Discriminant Updates
Machine Learning
The Relaxed Online Maximum Margin Algorithm
Machine Learning
A new approximate maximal margin classification algorithm
The Journal of Machine Learning Research
On the algorithmic implementation of multiclass kernel-based vector machines
The Journal of Machine Learning Research
Ultraconservative online algorithms for multiclass problems
The Journal of Machine Learning Research
ICML '05 Proceedings of the 22nd international conference on Machine learning
Online multiclass learning by interclass hypothesis sharing
ICML '06 Proceedings of the 23rd international conference on Machine learning
Online Passive-Aggressive Algorithms
The Journal of Machine Learning Research
Uncovering shared structures in multiclass classification
Proceedings of the 24th international conference on Machine learning
Online learning meets optimization in the dual
COLT'06 Proceedings of the 19th annual conference on Learning Theory
IEEE Transactions on Signal Processing
Hi-index | 0.00 |
In this work, we extend the ellipsoid method, which was originally designed for convex optimization, for online learning. The key idea is to approximate by an ellipsoid the classification hypotheses that are consistent with all the training examples received so far. This is in contrast to most online learning algorithms where only a single classifier is maintained at each iteration. Efficient algorithms are presented for updating both the centroid and the positive definite matrix of ellipsoid given a misclassified example. In addition to the classical ellipsoid method, an improved version for online learning is also presented. Mistake bounds for both ellipsoid methods are derived. Evaluation with the USPS dataset and three UCI data-sets shows encouraging results when comparing the proposed online learning algorithm to two state-of-the-art online learners.