Export Reviews, Discussions, Author Feedback and Meta-Reviews

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. The authors consider logistic regression when the data are contaminated with outliers. No assumptions are made on the outliers, they need not even follow any distribution, which can happen for example when a video is corrupted by sensor errors. The authors provide an innovative algorithm, RoLR, and provide performance guarantees. The algorithm is simple to describe but uses sophisticated ideas, and the mathematics behind the performance guarantees is impressive.