We study functions with multiple output values, and use active sampling to identify an example for each of the possible output values. Our results for this setting include: (1) Eff...
Many machine learning algorithms can be formulated in the framework of statistical independence such as the Hilbert Schmidt Independence Criterion. In this paper, we extend this c...
Xinhua Zhang, Le Song, Arthur Gretton, Alex J. Smo...
We consider the problem of uniformly sampling a vertex of a transportation polytope with m sources and n destinations, where m is a constant. We analyse a natural random walk on t...
We present exchange formulas that allow to express the stationary distribution of a continuous Markov chain with denumerable state-space having generator matrix Q∗ through a con...
We introduce a new system of trust analysis for concurrent and distributed systems using the π-calculus[13, 14, 15] as a modelling tool. A Type system using boolean annotations g...