Reinforcement learning addresses the dilemma between exploration to find profitable actions and exploitation to act according to the best observations already made. Bandit proble...
A h-uniform hypergraph H = (V, E) is called ( , k)-orientable if there exists an assignment of each hyperedge e ∈ E to exactly of its vertices v ∈ e such that no vertex is ass...
We present a novel approach to learn a kernelbased regression function. It is based on the use of conical combinations of data-based parameterized kernels and on a new stochastic ...
Pierre Machart, Thomas Peel, Liva Ralaivola, Sandr...
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)...
We address the problem of finding the most likely assignment or MAP estimation in a Markov random field. We analyze the linear programming formulation of MAP through the lens of...