Universal Approximation of Residual Flows in Maximum Mean Discrepancy

Abstract

Normalizing flows are a class of flexible deep generative models that offer easy likelihood computation. Despite their empirical success, there is little theoretical understanding of their expressiveness. In this work, we study residual flows, a class of normalizing flows composed of Lipschitz residual blocks. We prove residual flows are universal approximators in maximum mean discrepancy. We provide upper bounds on the number of residual blocks to achieve approximation under different assumptions.

Cite

Text

Kong and Chaudhuri. "Universal Approximation of Residual Flows in Maximum Mean Discrepancy." ICML 2021 Workshops: INNF, 2021.

Markdown

[Kong and Chaudhuri. "Universal Approximation of Residual Flows in Maximum Mean Discrepancy." ICML 2021 Workshops: INNF, 2021.](https://mlanthology.org/icmlw/2021/kong2021icmlw-universal/)

BibTeX

@inproceedings{kong2021icmlw-universal,
  title     = {{Universal Approximation of Residual Flows in Maximum Mean Discrepancy}},
  author    = {Kong, Zhifeng and Chaudhuri, Kamalika},
  booktitle = {ICML 2021 Workshops: INNF},
  year      = {2021},
  url       = {https://mlanthology.org/icmlw/2021/kong2021icmlw-universal/}
}