We propose a new method for comparing learning algorithms on multiple tasks which is based on a novel non-parametric test that we call the Poisson binomial test. The key aspect of...
It is well known that exploiting label correlations is important for multi-label learning. Existing approaches typically exploit label correlations globally, by assuming that the ...
In non-cooperative multi-agent situations, there cannot exist a globally optimal, yet opponent-independent learning algorithm. Regret-minimization over a set of strategies optimiz...
We consider incorporating action elimination procedures in reinforcement learning algorithms. We suggest a framework that is based on learning an upper and a lower estimates of th...