Divide-and-conquer potentials enable scalable and accurate predictions of forces and energies in atomistic systems
Literature Information
Stefano de Gironcoli
In committee of experts strategies, small datasets are extracted from a larger one and utilised for the training of multiple models. These models' predictions are then carefully weighted so as to obtain estimates which are dominated by the model(s) that are most informed in each domain of the data manifold. Here, we show how this divide-and-conquer philosophy provides an avenue in the making of machine learning potentials for atomistic systems, which is general across systems of different natures and efficiently scalable by construction. We benchmark this approach on various datasets and demonstrate that divide-and-conquer linear potentials are more accurate than their single model counterparts, while incurring little to no extra computational cost.
Related Literature
Copper–amyloid-β complex may catalyze peroxynitrite production in brain: evidence from molecular modeling
Ilaria Ciofini, Li Rao, Christian Amatore
DOI: 10.1039/C3CP54839B
Non-equilibrium segmental dynamics driven by multiwall carbon nanotubes in PS/PVME blends
Priti Xavier, Suryasarathi Bose
DOI: 10.1039/C4CP00832D
Enhanced photoluminescence and photoactivity of plasmon sensitized nSiNWs/TiO2 heterostructures
Vedi Kuyil Azhagan
DOI: 10.1039/C4CP01497A
Computational studies of electrochemical CO2 reduction on subnanometer transition metal clusters
Cong Liu, Haiying He, Peter Zapol, Larry A. Curtiss
DOI: 10.1039/C4CP02690J
Unveiling the effects of post-deposition treatment with different alkaline elements on the electronic properties of CIGS thin film solar cells
Fabian Pianezzi, Patrick Reinhard, Adrian Chirilă, Benjamin Bissig, Shiro Nishiwaki, Stephan Buecheler, Ayodhya N. Tiwari
DOI: 10.1039/C4CP00614C
Stress in titania nanoparticles: an atomistic study
Robert Darkins, Maria L. Sushko, Jun Liu, Dorothy M. Duffy
DOI: 10.1039/C3CP54357A
Effect of water on the transport properties of protic and aprotic imidazolium ionic liquids – an analysis of self-diffusivity, conductivity, and proton exchange mechanism
N. Yaghini, L. Nordstierna, A. Martinelli
DOI: 10.1039/C4CP00527A
Spectroscopic and viscometric elucidation of the interaction between a potential chloride channel blocker and calf-thymus DNA: the effect of medium ionic strength on the binding mode
Aniruddha Ganguly, Soumen Ghosh, Nikhil Guchhait
DOI: 10.1039/C4CP04175E
High DNP efficiency of TEMPONE radicals in liquid toluene at low concentrations
Nikolay Enkin, Guoquan Liu, Igor Tkach, Marina Bennati
DOI: 10.1039/C4CP00854E
Efficiency enhancement of black dye-sensitized solar cells by newly synthesized D–π–A coadsorbents: a theoretical study
Yavar T. Azar, Mahmoud Payami
DOI: 10.1039/C4CP00598H
You might also like
What are the main uses of 1H-Indazole-6-carbonitrile (CAS: 141290-59-7)?
1H-Indazole-6-carbonitrile finds applications in pharmaceuticals, where it serve...
How should waste containing Dioctyl (2E)-2-butenedioate (CAS: 2997-85-5) be handled?
Waste containing Dioctyl (2E)-2-butenedioate (CAS: 2997-85-5) should be collecte...
What industries use Sodium [(1,2-benzoxazol-3-ylmethyl)sulfonyl]azanide (CAS: 68291-98-5)?
Sodium [(1,2-benzoxazol-3-ylmethyl)sulfonyl]azanide is primarily used in pharmac...
Are there alternatives to Dimethyl 4-(4,4,5,5-tetramethyl-1,3,2-dioxaborolan-2-yl)-2,6-pyridinedicarboxylate (CAS: 741709-66-0) in synthesis?
Dimethyl 4-(4,4,5,5-tetramethyl-1,3,2-dioxaborolan-2-yl)-2,6-pyridinedicarboxyla...
How should waste containing 2-Fluoro-6-hydrazinopyridine (CAS: 80714-39-2) be handled?
Waste containing 2-Fluoro-6-hydrazinopyridine (CAS: 80714-39-2) should be manage...
What is 6-Formyl-2-pyridinecarboxylic acid (CAS: 499214-11-8)?
6-Formyl-2-pyridinecarboxylic acid is an organic compound with the molecular for...
What is the market or research trend for 3-(3,4-dimethoxyphenyl)-2,5-dimethyl-N-(2-morpholin-4-ylethyl)pyrazolo[1,5-a]pyrimidin-7-amine (CAS: 900874-91-1)?
Research trends for this compound indicate a focus on its potential applications...
How is 9H-Tribenzo[b,d,f]azepine (CAS: 29875-73-8) typically synthesized?
9H-Tribenzo[b,d,f]azepine is typically synthesized via a multi-step process invo...
How is 1-Cyclopropyl-7-ethoxy-6-fluoro-8-methoxy-4-oxo-1,4-dihydro-3-quinolinecarboxylic acid (CAS: 1797982-51-4) typically synthesized?
1-Cyclopropyl-7-ethoxy-6-fluoro-8-methoxy-4-oxo-1,4-dihydro-3-quinolinecarboxyli...
How should waste containing Methyl 3-oxo-1,2,3,4-tetrahydro-6-quinoxalinecarboxylate (CAS: 671820-52-3) be handled?
Waste containing Methyl 3-oxo-1,2,3,4-tetrahydro-6-quinoxalinecarboxylate (CAS: ...















