Bayes-Optimal Entropy Pursuit for Active Choice-Based Preference Learning

no code implementations • 24 Feb 2017 • Stephen N. Pallone, Peter I. Frazier, Shane G. Henderson

Under certain noise assumptions, we show that the Bayes-optimal policy for maximally reducing entropy of the posterior distribution of this linear classifier is a greedy policy, and that this policy achieves a linear lower bound when alternatives can be constructed from the continuum.

Active Learning