mlsanityData to 7 Oct 2026

Flows for Flows: Training Normalizing Flows Between Arbitrary Distributions with Maximum Likelihood Estimation

arXiv 2211.02487 ↗First posted 4 Nov 2022cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

Normalizing flows are constructed from a base distribution with a known density and a diffeomorphism with a tractable Jacobian. The base density of a normalizing flow can be parameterised by a different normalizing flow, thus allowing maps to be found between arbitrary distributions. We demonstrate and explore the utility of this approach and show it is particularly interesting in the case of conditional normalizing flows and for introducing optimal transport constraints on maps that are constructed using normalizing flows.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 5 of its 10 references that are in the map. First posted on arXiv 4 Nov 2022.

Builds on

5 of 10 references.

References · 5

  1. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  2. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,315
  3. 2019Neural Spline Flowscited by 590
  4. 2020Convex Potential Flows: Universal Probability Distributions with Optimal Transport and Convex Optimizationcited by 89
  5. 2020Simulation Assisted Likelihood-free Anomaly Detectioncited by 27

Built on by

Cited by year

Citing papers per year: 2023: 5.

5 papers.

  1. 2023Machine Learning for Anomaly Detection in Particle Physicscited by 29
  2. 2023CURTAINs Flows For Flows: Constructing Unobserved Regions with Maximum Likelihood Estimationcited by 10
  3. 2023Probabilistic and Semantic Descriptions of Image Manifolds and Their Applicationscited by 3
  4. 2023Decorrelation using Optimal Transportcited by 0
  5. 2023Arbitrary Distributions Mapping via SyMOT-Flow: A Flow-based Approach Integrating Maximum Mean Discrepancy and Optimal Transportcited by 0