Export Reviews, Discussions, Author Feedback and Meta-Reviews

"NIPS Neural Information Processing Systems 8-11th December 2014, Montreal, Canada",,, "Paper ID:","1871" "Title:","Parallel Feature Selection Inspired by Group Testing" Current Reviews First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. In this paper a novel and interesting parallel feature selection framework based on group testing is proposed for large scale data. As the author claimed, the presented method can speed up the feature selection algorithm and provide superior performance than other existing methods especially on very high dimensional dataset. The proposed framework for parallel feature selection is well defined with sufficient theoretical analysis. The author has proved that KL divergence and MI is C-separable under certain conditions.