Machine learning method for computation of optimal transitions in magnetic nanosystems
Nanosistemy: fizika, himiâ, matematika, Tome 11 (2020) no. 6, pp. 642-650
Cet article a éte moissonné depuis la source Math-Net.Ru
Minimum energy path (MEP) is an important tool for computation of activation barriers and transition rates for magnetic systems. Recently, new methods for numeric computation of MEP were proposed based on conjugate gradient and L-BFGS methods [1] significantly improved convergence rate compared to nudged elastic band (NEB) method. Due to lack of strict mathematical theory for MEP optimization other more effective methods are expected to exist. In this article, we propose a machine learning based approach to search for MEP computation methods. We reformulate the NEB method as a differentiable transformation in the space of all paths parametrized by a family of metaparameters. Using rate of convergence as the loss function, we train NEB optimizer to find optimal metaparameters. This meta learning technique can be the basis for deriving new optimization methods for computing MEP and other non-classical optimization problems.
Keywords:
Transition state, minimum energy path, machine learning, meta learning.
@article{NANO_2020_11_6_a3,
author = {K. R. Bushuev and I. S. Lobanov},
title = {Machine learning method for computation of optimal transitions in magnetic nanosystems},
journal = {Nanosistemy: fizika, himi\^a, matematika},
pages = {642--650},
year = {2020},
volume = {11},
number = {6},
language = {en},
url = {http://geodesic.mathdoc.fr/item/NANO_2020_11_6_a3/}
}
TY - JOUR AU - K. R. Bushuev AU - I. S. Lobanov TI - Machine learning method for computation of optimal transitions in magnetic nanosystems JO - Nanosistemy: fizika, himiâ, matematika PY - 2020 SP - 642 EP - 650 VL - 11 IS - 6 UR - http://geodesic.mathdoc.fr/item/NANO_2020_11_6_a3/ LA - en ID - NANO_2020_11_6_a3 ER -
K. R. Bushuev; I. S. Lobanov. Machine learning method for computation of optimal transitions in magnetic nanosystems. Nanosistemy: fizika, himiâ, matematika, Tome 11 (2020) no. 6, pp. 642-650. http://geodesic.mathdoc.fr/item/NANO_2020_11_6_a3/