We give a provably correct algorithm to reconstruct a kdimensional manifold embedded in d-dimensional Euclidean space. Input to our algorithm is a point sample coming from an unkn...
We consider the problem of finding a matching between two sets of features, given complex relations among them, going beyond pairwise. Each feature set is modeled by a hypergraph ...
There are two main families of on-line algorithms depending on whether a relative entropy or a squared Euclidean distance is used as a regularizer. The difference between the two f...
Traditionally, combinatorial optimization problems (such as maximum flow, maximum matching, etc.) have been studied for networks where each link has a fixed capacity. Recent resear...
Yossi Azar, Aleksander Madry, Thomas Moscibroda, D...
—In graph-based learning models, entities are often represented as vertices in an undirected graph with weighted edges describing the relationships between entities. In many real...