A learning problem might have several measures of complexity (e.g., norm and dimensionality) that affect the generalization error. What is the interaction between these complexiti...
Abstract. We introduce "matroid parse trees" which, using only a limited amount of information at each node, can build up the vector representations of matroids of bounde...
We introduce a new method -- the group Dantzig selector -- for high dimensional sparse regression with group structure, which has a convincing theory about why utilizing the group...
In this paper we investigate the computational complexity of knot theoretic problems and show upper and lower bounds for planarity problem of signed and unsigned knot diagrams repr...
An extension of the simply-typed lambda calculus is presented which contains both well-structured inductive and coinductive types, and which also identifies a class of types for w...