Sequential Information Maximization: When is Greedy Near-optimal?
published: Aug. 20, 2015, recorded: July 2015, views: 1957
Report a problem or upload filesIf you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
Optimal information gathering is a central challenge in machine learning and science in general. A common objective that quantifies the usefulness of observations is Shannon's mutual information, defined w.r.t. a probabilistic model. Greedily selecting observations that maximize the mutual information is the method of choice in numerous applications, ranging from Bayesian experimental design to automated diagnosis, to active learning in Bayesian models. Despite its importance and widespread use in applications, little is known about the theoretical properties of sequential information maximization, in particular under noisy observations. In this paper, we analyze the widely used greedy policy for this task, and identify problem instances where it provides provably near-maximal utility, even in the challenging setting of persistent noise. Our results depend on a natural separability condition associated with a channel injecting noise into the observations. We also show that this separability condition is necessary: If it does not hold, the greedy policy can fail to select informative observations.
Download slides: colt2015_chen_information_maximization_01.pdf (3.8 MB)
Link this pageWould you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !