Privacy preserving is an important issue in learning.

These authors contributed equally to this work.

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

Data augmentation is a ubiquitous technique for increasing the size of labeled training sets by leveraging task-specific data transformations that preserve class labels.

Our main contribution is the first bias-variance bound for the problem of learning Gaussian mixtures with streaming data.

Reconstruction of low-rank matrices from noisy and otherwise contaminated data is a key problem in machine learning, computer vision and data science.

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

We show that, compared to earlier works, it is less inclined to be stuck in trivial solutions and avoids the need for a strong generative model.

This paper studies the problem of learning a low-dimensional Euclidean metric from comparative judgments.

Our experiments show that hash embeddings can easily deal with huge vocabularies consisting of millions of tokens.