This paper studies efficient learning with respect to mind changes. Our starting point is the idea that a learner that is efficient with respect to mind changes minimizes mind cha...
Experimentation of new algorithms is the usual companion section of papers dealing with SAT. However, the behavior of those algorithms is so unpredictable that even strong experime...
In the multi-armed bandit (MAB) problem there are k distributions associated with the rewards of playing each of k strategies (slot machine arms). The reward distributions are ini...
A fundamental assumption often made in supervised classification is that the problem is static, i.e. the description of the classes does not change with time. However many practi...
The on-line algorithms in machine learning are intended to discover unknown function of the domain based on incremental observing of it instance by instance. These algorithms have...
Helen Kaikova, Vagan Y. Terziyan, Borys Omelayenko