First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. This paper presents the first finite sample analysis of k-NN density estimation and mode estimation. The paper is well-written and the results are novel and appear to be correct. I think the results are quite impressive and, because mode estimation plays an important role in density-based clustering, the results are important. My only negative comment is that there are no numerical experiments.

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

The proliferation of automated inference algorithms in Bayesian statistics has provided practitioners newfound access to fast, reproducible data analysis and powerful statistical models.

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

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

We explore combining dropout with robust training methods and obtain better generalization.

However, these models do not offer exact density evaluation, and can be difficult to train.

Learning-to-learn or meta-learning leverages data-driven inductive bias to increase the efficiency of learning on a novel task.

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. Dropout in deep neural networks is perturbing the output layer after non-linear mapping. Later it has been shown that this is closely related to perturbing the weight matrix before non-linear mapping due to the choice of mapping functions in neural networks (known as DropConnect). In a way, both Dropout and DropConnect perturb the decision boundary (ie parameter) after training, which is different from (though might be related to) perturbing the input feature vectors before training. This paper provides generalization bounds for training with perturbed features, which is more closely related to learning by feature deletion [13] or learning with corrupted features [9].