Machine learning enhanced global optimization by clustering local environments to enable bundled atomic energies

Abstract

We show how to speed up global optimization of molecular structures using machine learning methods. To represent the molecular structures we introduce the auto-bag feature vector that combines: i) a local feature vector for each atom, ii) an unsupervised clustering of such feature vectors for many atoms across several structures, and iii) a count for a given structure of how many times each cluster is represented. During subsequent global optimization searches, accumulated structure-energy relations of relaxed structural candidates are used to assign local energies to each atom using supervised learning. Specifically, the local energies follow from assigning energies to each cluster of local feature vectors and demanding the sum of local energies to amount to the structural energies in the least squares sense. The usefulness of the method is demonstrated in basin hopping searches for 19-atom structures described by single-or double-well Lennard-Jones type potentials and for 24 atom carbon structures described by density functional theory (DFT). In all cases, utilizing the local energy information derived on-the-fly enhances the rate at which the global minimum energy structure is found. arXiv:1807.04605v2 [physics.comp-ph]

The Artificial Bee Colony Algorithm for Global Optimization of Nanosized Clusters

“…To overcome this barrier, one way is to do a screen with some cheap methods (like using xTB in this paper); another way is to incorporate data science methods, like machine learning, to improve the global optimization algorithm. 95,96 Anyway, the new algorithm has made ABCluster a more convenient and powerful tool for solving theoretical and experimental problems in catalysis, material, and energy chemistry, etc.…”

Hyperparameter optimization for recommender systems through Bayesian optimization

“…Recently, Bayesian optimization (BO) (Shahriari et al 2015;Frazier 2018) is becoming one of the most widely adopted strategies for global optimization of multi-extremal, and expensive-to-evaluate objective functions related to, e.g., sensor networks (Garnett et al 2010), drug design (Meldgaard et al 2018), time-series forecasting (Candelieri et al 2018a), inversion problems (Perdikaris and Karniadakis 2016; Galuzzi et al 2018), and robotics (Olofsson et al 2018).…”

Machine learning for potential energy surfaces: An extensive database and assessment of methods

“…54,55 Hammer and co-workers showed how to combine evolutionary algorithms with ML techniques to find minimum energy structures, which can potentially be used for the targeted design of molecules. [56][57][58] Thus, there are many new potentially helpful algorithms for the theoretical chemical community, and it is not clear yet which of these new approaches will become a standard in the future. The aim of this work is therefore a prescreening of suitable ML algorithms that can be useful in the context of describing PESs, and the production of a large database to be used in further benchmarks.…”