English

Representation Learning: A Statistical Perspective

Machine Learning 2019-11-27 v1 Machine Learning

Abstract

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.

Keywords

Cite

@article{arxiv.1911.11374,
  title  = {Representation Learning: A Statistical Perspective},
  author = {Jianwen Xie and Ruiqi Gao and Erik Nijkamp and Song-Chun Zhu and Ying Nian Wu},
  journal= {arXiv preprint arXiv:1911.11374},
  year   = {2019}
}