3871bd64012152bfb53fdf04b401193f-Reviews.html

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. The authors study the problem of binary classification in the presence of random, class-conditional noise in the training data. They propose two approaches based on a suitable modification of a given surrogate loss function and derive performance bounds. More specifically, they provide guarantees for risk minimization of convex surrogates under random label noise in the general setting, and without any assumptions on the true distribution. Moreover, they provide two alternative approaches for modifying a given surrogate loss function.