In this paper we consider two online multi-class classification problems: classification with linear models and with kernelized models. The predictions can be thought of as probability distributions. The quality of predictions is measured by the Brier loss function. We suggest two computationally efficient algorithms to work with these problems, the second algorithm is derived by considering a new class of linear prediction models. We prove theoretical guarantees on the cumulative losses of the algorithms. We kernelize one of the algorithms and prove theoretical guarantees on the loss of the kernelized version. We perform experiments and compare our algorithms with logistic regression. © 2010 IFIP.
CITATION STYLE
Zhdanov, F., & Kalnishkan, Y. (2010). Linear probability forecasting. In IFIP Advances in Information and Communication Technology (Vol. 339 AICT, pp. 4–11). Springer New York LLC. https://doi.org/10.1007/978-3-642-16239-8_4
Mendeley helps you to discover research relevant for your work.