We consider the problem of active sequential hypothesis testing where a Bayesian decision maker must infer the true hypothesis from a set of hypotheses. The decision maker may choose for a set of actions, where the outcome of an action is corrupted by independent noise. In this paper we consider a special case where the decision maker has limited knowledge about the distribution of observations for each action, in that only a binary value is observed. Our objective is to infer the true hypothesis with low error, while minimizing the number of action sampled. Our main results include the derivation of a lower bound on sample size for our system under limited knowledge and the design of an active learning policy that matches this lower bound and outperforms similar known algorithms.
Fabio Cecchi (Eindhoven University of Technology)
I am currently a PhD student in Mathematics (Stochastic Operations Research group) at Eindhoven University of Technology, EIndhoven, The Netherlands. I will defend my thesis on February 1st, 2018, and I am currently looking for job opportunities. My current research interests span from applied probability (stochastic networks, stochastic scheduling, queueing theory) to learning theory.