e6d8545daa42d5ced125a4bf747b3688-Reviews.html

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. This paper provides a generic way to perform parameter tuning of a given training algorithm in a deferentially private manner. Given a set of examples (for training and validation), a set of model parameters, a training algorithm, and a performance measure, the proposed procedure outputs a deferentially private hypothesis with respect to the prescribed privacy parameter. The basis behind the procedure is the definition of (\beta_1, \beta_2, \delta)-stability; which describes the stability of the performance with respect to change in the training set and the validation set. The procedure basically follows the exponential mechanism, and the utility bound is also provided.