Cargando…
A Score-Based Approach for Training Schrödinger Bridges for Data Modelling
A Schrödinger bridge is a stochastic process connecting two given probability distributions over time. It has been recently applied as an approach for generative data modelling. The computational training of such bridges requires the repeated estimation of the drift function for a time-reversed stoc...
Autores principales: | Winkler, Ludwig, Ojeda, Cesar, Opper, Manfred |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9955847/ https://www.ncbi.nlm.nih.gov/pubmed/36832682 http://dx.doi.org/10.3390/e25020316 |
Ejemplares similares
-
Stochastic Control for Bayesian Neural Network Training
por: Winkler, Ludwig, et al.
Publicado: (2022) -
Solving Schrödinger Bridges via Maximum Likelihood
por: Vargas, Francisco, et al.
Publicado: (2021) -
Variational Bayesian Inference for Nonlinear Hawkes Process with Gaussian Process Self-Effects
por: Malem-Shinitski, Noa, et al.
Publicado: (2022) -
Quantifying brain state transition cost via Schrödinger Bridge
por: Kawakita, Genji, et al.
Publicado: (2022) -
Schrodinger handbag model
por: Bell, J S
Publicado: (1977)