We propose online decision strategies for time-dependent sequences of linear programs which use no distributional and minimal geometric assumptions about the data. These strategies...
Tatsiana Levina, Yuri Levin, Jeff McGill, Mikhail ...
In this paper the sequential prediction problem with expert advice is considered when the loss is unbounded under partial monitoring scenarios. We deal with a wide class of the par...
Abstract. Oza’s Online Boosting algorithm provides a version of AdaBoost which can be trained in an online way for stationary problems. One perspective is that this enables the p...
Adam Pocock, Paraskevas Yiapanis, Jeremy Singer, M...
Some online algorithms for linear classification model the uncertainty in their weights over the course of learning. Modeling the full covariance structure of the weights can prov...
Justin Ma, Alex Kulesza, Mark Dredze, Koby Crammer...
In recent years there have been efforts to develop a probabilistic framework to explain the workings of a Learning Classifier System. This direction of research has met with lim...