40008b9a5380fcacce3976bf7c08af5b-Reviews.html

A relevant and well-written technical paper, which presents a variation of the classic active learning setting coined'auditing'. This is generally defined by non-uniform cost of labels and not knowing the cost of a label a priori to the label query. The aim of the paper is to compare the complexity of auditing versus (standard) active learning, i.e., how many labels are required. The authors accomplishes this by deriving bounds on the complexity for the new variant and compares to standard active learning where they show interesting results. The authors focuses on two (tractable) cases: 1) They consider the active learning complexity as the total number of label queries.