Semi-supervised learning aims at taking advantage of unlabeled data to improve the efficiency of supervised learning procedures. For discriminative models however, this is a chall...
This paper introduces a novel multiagent learning algorithm, Convergence with Model Learning and Safety (or CMLeS in short), which achieves convergence, targeted optimality agains...
ended abstract summarizes the research presented in Dr. Pardoe’s recently-completed Ph.D. thesis [Pardoe 2011]. The thesis considers how adaptive trading agents can take advantag...
We present new results on the well-studied problem of learning DNF expressions. We prove that an algorithm due to Kushilevitz and Mansour [13] can be used to weakly learn DNF form...
Avrim Blum, Merrick L. Furst, Jeffrey C. Jackson, ...
This paper introduces a new SAT solver that integrates logicbased reasoning and integer programming methods to systems of CNF and PB constraints. Its novel features include an eff...