We present a new family of subgradient methods that dynamically incorporate knowledge of the geometry of the data observed in earlier iterations to perform more informative gradie...
We consider an online learning setting where at each time step the decision maker has to choose how to distribute the future loss between k alternatives, and then observes the los...
We develop an online algorithm called Component Hedge for learning structured concept classes when the loss of a structured concept sums over its components. Example classes inclu...
Wouter M. Koolen, Manfred K. Warmuth, Jyrki Kivine...
We describe online algorithms for learning a rotation from pairs of unit vectors in Rn . We show that the expected regret of our online algorithm compared to the best fixed rotati...
One of the most widely used techniques for data clustering is agglomerative clustering. Such algorithms have been long used across many different fields ranging from computational...