Taming hyperparameter tuning in continuous normalizing flows using the JKO scheme
Abstract A normalizing flow (NF) is a mapping that transforms a chosen probability distribution to a normal distribution. Such flows are a common technique used for data generation and density estimation in machine learning and data science. The density estimate obtained with a NF requires a change...
Main Authors: | Alexander Vidal, Samy Wu Fung, Luis Tenorio, Stanley Osher, Levon Nurbekyan |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2023-03-01
|
Series: | Scientific Reports |
Online Access: | https://doi.org/10.1038/s41598-023-31521-y |
Similar Items
-
L∞ estimates for the JKO scheme in parabolic-elliptic Keller-Segel systems
by: Carrillo, JA, et al.
Published: (2017) -
Refining the ONCE Benchmark With Hyperparameter Tuning
by: Maksim Golyadkin, et al.
Published: (2024-01-01) -
The tame fundamental group of a formal neighbourhood of a divisor with normal crossings on scheme/
by: 185594 Grohtendieck, Alexander, et al.
Published: (1971) -
Practical Bayesian optimisation for hyperparameter tuning
by: Alvi, AS
Published: (2020) -
Practical Bayesian optimisation for hyperparameter tuning
by: Alvi, A
Published: (2019)