We study the problem of learning a real-valued function that satisfies the Demographic Parity constraint. It demands the distribution of the predicted output to be independent of the sensitive attribute. We consider the case that the sensitive attribute is available for prediction.

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. The authors propose a new screening rule Slores for pre-filtering variables for logistic regression. This statement though sounds too simple and doesn't give the paper justice at all. The paper provides a rigorous and theoretically well founded derivation of a novel pre-screening rule which could in principle be extended to other settings as well. The method is also efficient compared to other safe rules that guarantee to discard only non-zero entries.

Although many recent efforts have been devoted to its efficient implementation, its application to high dimensional data still poses significant challenges. In this paper, we present a fast and effective sparse lo gistic regression s creening rule (Slores) to identify the "0" components in the solution vector, which may lead to a substantial reduction in the number of features to be entered to the optimization. An appealing feature of Slores is that the data set needs to be scanned only once to run the screening and its computational cost is negligible compared to that of solving the sparse logistic regression problem. Moreover, Slores is independent of solvers for sparse logistic regression, thus Slores can be integrated with any existing solver to improve the efficiency. We have evaluated Slores using high-dimensional data sets from different applications. Experiments demonstrate that Slores outperforms the existing state-of-the-art screening rules and the efficiency of solving sparse logistic regression can be improved by one magnitude.

Such pairwise comparison data is easy to collect, as typically discussed in the learning-to-rank scenario, and does not break the anonymity of data.

Neural Information Processing Systems http://nips.cc/

It also does not enjoy SNIS's inherent stability and boundedness.