Representation Learning: A Statistical Perspective
This is an incremental review article for researchers in statistics and machine learning, summarizing existing work without tackling a specific problem.
The paper reviews recent advances in representation learning from a statistical perspective, focusing on unsupervised learning of vector and matrix representations, but does not present new results or concrete numbers.
Learning representations of data is an important problem in statistics and machine learning. While the origin of learning representations can be traced back to factor analysis and multidimensional scaling in statistics, it has become a central theme in deep learning with important applications in computer vision and computational neuroscience. In this article, we review recent advances in learning representations from a statistical perspective. In particular, we review the following two themes: (a) unsupervised learning of vector representations and (b) learning of both vector and matrix representations.