We explore a general Bayesian active learning setting, in which the learner can ask arbitrary yes/no questions. We derive upper and lower bounds on the expected number of queries r...
We use game theory to analyze meta-learning algorithms. The objective of meta-learning is to determine which algorithm to apply on a given task. This is an instance of a more gene...
Background: Position-specific priors have been shown to be a flexible and elegant way to extend the power of Gibbs sampler-based motif discovery algorithms. Information of many ty...
This paper is concerned with information revelation in single-item auctions. We compute how much data needs to be transmitted in three strategically equivalent auctions--the Vickr...
Elena Grigorieva, P. Jean-Jacques Herings, Rudolf ...
In this paper, an event-centric commodity trading simulation powered by the multiagent framework is presented. The purpose of this simulation platform is for training novice trade...