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...
Enregistré dans:
Auteurs principaux: | Oleksandr Borysenko, Maksym Byshkin |
---|---|
Format: | article |
Langue: | EN |
Publié: |
Nature Portfolio
2021
|
Sujets: | |
Accès en ligne: | https://doaj.org/article/9ae814904dc54f65a9749af760cb5d73 |
Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
Documents similaires
-
Inferring temporal dynamics from cross-sectional data using Langevin dynamics
par: Pritha Dutta, et autres
Publié: (2021) -
OPTIMIZATION OF DOUBLY REINFORCED BEAM DESIGN USING SIMULATED ANNEALING
par: SIMON OLAYIWOLA ADEREMI OLAWALE, et autres
Publié: (2020) -
OPTIMIZATION OF SINGLY REINFORCED BEAM DESIGN USING SIMULATED ANNEALING
par: SIMON OLAYIWOLA ADEREMI OLAWALE, et autres
Publié: (2021) -
A strong diffusive ion mode in dense ionized matter predicted by Langevin dynamics
par: P. Mabey, et autres
Publié: (2017) -
Optimization of substation grounding grid design for horizontal and vertical multilayer and uniform soil condition using Simulated Annealing method.
par: Navinesshani Permal, et autres
Publié: (2021)