mlsanityData to 7 Oct 2026

Generalization of the Change of Variables Formula with Applications to Residual Flows

arXiv 2107.04346 ↗First posted 9 Jul 2021stat.ML cs.LG math.DScited by 1

Not on the map. Why?

Abstract (arXiv)

Normalizing flows leverage the Change of Variables Formula (CVF) to define flexible density models. Yet, the requirement of smooth transformations (diffeomorphisms) in the CVF poses a significant challenge in the construction of these models. To enlarge the design space of flows, we introduce L-diffeomorphisms as generalized transformations which may violate these requirements on zero Lebesgue-measure sets. This relaxation allows e.g. the use of non-smooth activation functions such as ReLU. Finally, we apply the obtained results to planar, radial, and contractive residual flows.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 8 of its 22 references that are in the map. First posted on arXiv 9 Jul 2021.

Builds on

8 of 22 references.

References · 8

  1. 2015Variational Inference with Normalizing Flowscited by 2,161
  2. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,315
  3. 2018Invertible Residual Networkscited by 364
  4. 2019Residual Flows for Invertible Generative Modelingcited by 256
  5. 2018Neural Autoregressive Flowscited by 207
  6. 2018Sylvester Normalizing Flows for Variational Inferencecited by 71
  7. 2019Sum-of-Squares Polynomial Flowcited by 62
  8. 2020The Expressive Power of a Class of Normalizing Flow Modelscited by 35

Built on by

Cited by year

Citing papers per year: 2023: 1.

1 paper.