This paper studies sequence prediction based on the monotone Kolmogorov complexity Km=−log m, i.e. based on universal deterministic/one-part MDL. m is extremely close to Solomon...
The usage of Gaussian mixture models for video segmentation has been widely adopted. However, the main difficulty arises in choosing the best model complexity. High complex models ...
Boosting algorithms are procedures that "boost" low-accuracy weak learning algorithms to achieve arbitrarily high accuracy. Over the past decade boosting has been widely...
Abstract. We study online learning algorithms that predict by combining the predictions of several subordinate prediction algorithms, sometimes called “experts.” These simple a...
Yoav Freund, Robert E. Schapire, Yoram Singer, Man...
This paper shows how universal learning can be achieved with expert advice. To this aim, we specify an experts algorithm with the following characteristics: (a) it uses only feedba...