CoolMomentum: a method for stochastic optimization by Langevin dynamics with simulated annealing
Abstract Deep learning applications require global optimization of non-convex objective functions, which have multiple local minima. The same problem is often found in physical simulations and may be resolved by the methods of Langevin dynamics with Simulated Annealing, which is a well-established a...
Guardado en:
Autores principales: | Oleksandr Borysenko, Maksym Byshkin |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Nature Portfolio
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/9ae814904dc54f65a9749af760cb5d73 |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
Ejemplares similares
-
Inferring temporal dynamics from cross-sectional data using Langevin dynamics
por: Pritha Dutta, et al.
Publicado: (2021) -
OPTIMIZATION OF DOUBLY REINFORCED BEAM DESIGN USING SIMULATED ANNEALING
por: SIMON OLAYIWOLA ADEREMI OLAWALE, et al.
Publicado: (2020) -
OPTIMIZATION OF SINGLY REINFORCED BEAM DESIGN USING SIMULATED ANNEALING
por: SIMON OLAYIWOLA ADEREMI OLAWALE, et al.
Publicado: (2021) -
A strong diffusive ion mode in dense ionized matter predicted by Langevin dynamics
por: P. Mabey, et al.
Publicado: (2017) -
Optimization of substation grounding grid design for horizontal and vertical multilayer and uniform soil condition using Simulated Annealing method.
por: Navinesshani Permal, et al.
Publicado: (2021)