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 paper proposes a new penalty term that can be used in learning a regression model; it's based on the idea that features are grouped into (possibly overlapping) groups and the penalty term discourages the use of nonzero weights for several features from the same group. The paper describes how to solve the resulting optimization problem and presents an evaluation on several synthetic and realistic datasets, demonstrating that the proposed approach works better than several alternatives. The paper is clearly written and well organized, and seems to present an interesting incremental improvement on various earlier LASSO methods (which are mentioned in the related work section). Comments for the authors: exclusive group LASSO [caption of Figure 1] -- should be Exclusive Eq.(2) [caption of Figure 1] -- space missing; there are several similar occurrences elsewhere G_g \in P({1, 2, ..., p}) denotes a set of group g [page 2] -- I found this sentence unclear.