Export Reviews, Discussions, Author Feedback and Meta-Reviews

Significance: This paper belongs to an important class of algorithms that allow one to choose between privacy and accuracy. If data privacy continues to be in the public spotlight, this paper could be a nice addition to that field. Originality: To this reader's knowledge, their approach is novel, borrowing from common techniques in privacy aware learning. Q2: Please summarize your review in 1-2 sentences The paper illustrates a nice application of privacy aware learning to recommendation systems. Further experiments would strengthen the reader's understanding of how the algorithm performs, whether it meets its privacy goals, and how it compares to previous methods.