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

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. This paper provides some theoretical analysis on Positive and Unlabeled Data learning (PU), when only the positive instances and unlabeled instances are available. The authors show that learning from PU is equivalent to a cost-sensitive classification task if the label prior is known. The main contribution of the paper is that, the authors show that using any convex loss leads to inconsistent classifier for PU tasks. Instead, using a non-convex ramp loss gives a consistent estimator. This theoretical justification is supported by experiments, which demonstrate that adopting hinge loss of SVM may result in very bad classification error comparing to using the non-convex ramp loss.

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

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

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

Based on the feedback, we will try to re-write this section more clearly as well.

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. This paper presents an unsupervised dimensionality reduction algorithm which is based on the information bottleneck (IB) method. The method optimizes a constrained objective which, like the IB method, is comprised of the mutual information criteria. The criteria are between a joint density of discrete observed variables and the densities of a set of discrete latent factors, and between factored densities of the observed variables and the latent factors' densities. The goal of the the objective function is to infer latent factors such that by conditioning on them, the observed variables can be factorized into subsets of minimally correlated elements.