Birch and Tverberg partitions are closely related concepts from discrete geometry. We show two properties for the number of Birch partitions: Evenness, and a lower bound. This imp...
We present a new method for transductive learning, which can be seen as a transductive version of the k nearest-neighbor classifier. Unlike for many other transductive learning me...
We develop a high dimensional nonparametric classification method named sparse additive machine (SAM), which can be viewed as a functional version of support vector machine (SVM)...
One of the best ways of studying ordered algebraic structures is through their spectra. The three well-known spectra usually considered are the Brumfiel, Keimel, and the maximal sp...
We introduce the first algorithm for off-policy temporal-difference learning that is stable with linear function approximation. Off-policy learning is of interest because it forms...