English

ELF: Exact-Lipschitz Based Universal Density Approximator Flow

Machine Learning 2021-12-15 v1 Machine Learning

Abstract

Normalizing flows have grown more popular over the last few years; however, they continue to be computationally expensive, making them difficult to be accepted into the broader machine learning community. In this paper, we introduce a simple one-dimensional one-layer network that has closed form Lipschitz constants; using this, we introduce a new Exact-Lipschitz Flow (ELF) that combines the ease of sampling from residual flows with the strong performance of autoregressive flows. Further, we show that ELF is provably a universal density approximator, more computationally and parameter efficient compared to a multitude of other flows, and achieves state-of-the-art performance on multiple large-scale datasets.

Keywords

Cite

@article{arxiv.2112.06997,
  title  = {ELF: Exact-Lipschitz Based Universal Density Approximator Flow},
  author = {Achintya Gopal},
  journal= {arXiv preprint arXiv:2112.06997},
  year   = {2021}
}
R2 v1 2026-06-24T08:15:49.034Z