Fast and flexible range-separated models for atomistic machine learning
Most atomistic machine learning (ML) models rely on a locality ansatz, and decompose the energy into a sum of short-ranged, atom-centered contributions. This leads to clear limitations when trying to describe problems that are dominated by long-range physical effects - most notably electrostatics. M...
Gespeichert in:
Veröffentlicht in: | arXiv.org 2024-12 |
---|---|
Hauptverfasser: | , , , , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | |
container_start_page | |
container_title | arXiv.org |
container_volume | |
creator | Loche, Philip Huguenin-Dumittan, Kevin K Honarmand, Melika Xu, Qianjun Rumiantsev, Egor Wei Bin How Langer, Marcel F Ceriotti, Michele |
description | Most atomistic machine learning (ML) models rely on a locality ansatz, and decompose the energy into a sum of short-ranged, atom-centered contributions. This leads to clear limitations when trying to describe problems that are dominated by long-range physical effects - most notably electrostatics. Many approaches have been proposed to overcome these limitations, but efforts to make them efficient and widely available are hampered by the need to incorporate an ad hoc implementation of methods to treat long-range interactions. We develop a framework aiming to bring some of the established algorithms to evaluate non-bonded interactions - including Ewald summation, classical particle-mesh Ewald (PME), and particle-particle/particle-mesh (P3M) Ewald - into atomistic ML. We provide a reference implementation for PyTorch as well as an experimental one for JAX. Beyond Coulomb and more general long-range potentials, we introduce purified descriptors which disregard the immediate neighborhood of each atom, and are more suitable for general long-ranged ML applications. Our implementations are fast, feature-rich, and modular: They provide an accurate evaluation of physical long-range forces that can be used in the construction of (semi)empirical baseline potentials; they exploit the availability of automatic differentiation to seamlessly combine long-range models with conventional, local ML schemes; and they are sufficiently flexible to implement more complex architectures that use physical interactions as building blocks. We benchmark and demonstrate our torch-pme and jax-pme libraries to perform molecular dynamics simulations, to train range-separated ML potentials, and to evaluate long-range equivariant descriptors of atomic structures. |
format | Article |
fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_3141256672</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3141256672</sourcerecordid><originalsourceid>FETCH-proquest_journals_31412566723</originalsourceid><addsrcrecordid>eNqNjkEOgjAQABsTE4nyh008k0AL6N2IPsA7WWGLJaXFbkl8vhx8gKc5zBxmIxKpVJGdSyl3ImUe8zyX9UlWlUrErUGOgK4HbeljnpYgoBsoY5oxYKQeJt-TZdA-AEY_GY6mgwm7l3EEljA444aD2Gq0TOmPe3Fsro_LPZuDfy_EsR39EtyqWlWUhazq9UD9V30BDn070g</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3141256672</pqid></control><display><type>article</type><title>Fast and flexible range-separated models for atomistic machine learning</title><source>Freely Accessible Journals</source><creator>Loche, Philip ; Huguenin-Dumittan, Kevin K ; Honarmand, Melika ; Xu, Qianjun ; Rumiantsev, Egor ; Wei Bin How ; Langer, Marcel F ; Ceriotti, Michele</creator><creatorcontrib>Loche, Philip ; Huguenin-Dumittan, Kevin K ; Honarmand, Melika ; Xu, Qianjun ; Rumiantsev, Egor ; Wei Bin How ; Langer, Marcel F ; Ceriotti, Michele</creatorcontrib><description>Most atomistic machine learning (ML) models rely on a locality ansatz, and decompose the energy into a sum of short-ranged, atom-centered contributions. This leads to clear limitations when trying to describe problems that are dominated by long-range physical effects - most notably electrostatics. Many approaches have been proposed to overcome these limitations, but efforts to make them efficient and widely available are hampered by the need to incorporate an ad hoc implementation of methods to treat long-range interactions. We develop a framework aiming to bring some of the established algorithms to evaluate non-bonded interactions - including Ewald summation, classical particle-mesh Ewald (PME), and particle-particle/particle-mesh (P3M) Ewald - into atomistic ML. We provide a reference implementation for PyTorch as well as an experimental one for JAX. Beyond Coulomb and more general long-range potentials, we introduce purified descriptors which disregard the immediate neighborhood of each atom, and are more suitable for general long-ranged ML applications. Our implementations are fast, feature-rich, and modular: They provide an accurate evaluation of physical long-range forces that can be used in the construction of (semi)empirical baseline potentials; they exploit the availability of automatic differentiation to seamlessly combine long-range models with conventional, local ML schemes; and they are sufficiently flexible to implement more complex architectures that use physical interactions as building blocks. We benchmark and demonstrate our torch-pme and jax-pme libraries to perform molecular dynamics simulations, to train range-separated ML potentials, and to evaluate long-range equivariant descriptors of atomic structures.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Algorithms ; Availability ; Electrostatics ; Machine learning ; Molecular dynamics</subject><ispartof>arXiv.org, 2024-12</ispartof><rights>2024. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>776,780</link.rule.ids></links><search><creatorcontrib>Loche, Philip</creatorcontrib><creatorcontrib>Huguenin-Dumittan, Kevin K</creatorcontrib><creatorcontrib>Honarmand, Melika</creatorcontrib><creatorcontrib>Xu, Qianjun</creatorcontrib><creatorcontrib>Rumiantsev, Egor</creatorcontrib><creatorcontrib>Wei Bin How</creatorcontrib><creatorcontrib>Langer, Marcel F</creatorcontrib><creatorcontrib>Ceriotti, Michele</creatorcontrib><title>Fast and flexible range-separated models for atomistic machine learning</title><title>arXiv.org</title><description>Most atomistic machine learning (ML) models rely on a locality ansatz, and decompose the energy into a sum of short-ranged, atom-centered contributions. This leads to clear limitations when trying to describe problems that are dominated by long-range physical effects - most notably electrostatics. Many approaches have been proposed to overcome these limitations, but efforts to make them efficient and widely available are hampered by the need to incorporate an ad hoc implementation of methods to treat long-range interactions. We develop a framework aiming to bring some of the established algorithms to evaluate non-bonded interactions - including Ewald summation, classical particle-mesh Ewald (PME), and particle-particle/particle-mesh (P3M) Ewald - into atomistic ML. We provide a reference implementation for PyTorch as well as an experimental one for JAX. Beyond Coulomb and more general long-range potentials, we introduce purified descriptors which disregard the immediate neighborhood of each atom, and are more suitable for general long-ranged ML applications. Our implementations are fast, feature-rich, and modular: They provide an accurate evaluation of physical long-range forces that can be used in the construction of (semi)empirical baseline potentials; they exploit the availability of automatic differentiation to seamlessly combine long-range models with conventional, local ML schemes; and they are sufficiently flexible to implement more complex architectures that use physical interactions as building blocks. We benchmark and demonstrate our torch-pme and jax-pme libraries to perform molecular dynamics simulations, to train range-separated ML potentials, and to evaluate long-range equivariant descriptors of atomic structures.</description><subject>Algorithms</subject><subject>Availability</subject><subject>Electrostatics</subject><subject>Machine learning</subject><subject>Molecular dynamics</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><recordid>eNqNjkEOgjAQABsTE4nyh008k0AL6N2IPsA7WWGLJaXFbkl8vhx8gKc5zBxmIxKpVJGdSyl3ImUe8zyX9UlWlUrErUGOgK4HbeljnpYgoBsoY5oxYKQeJt-TZdA-AEY_GY6mgwm7l3EEljA444aD2Gq0TOmPe3Fsro_LPZuDfy_EsR39EtyqWlWUhazq9UD9V30BDn070g</recordid><startdate>20241204</startdate><enddate>20241204</enddate><creator>Loche, Philip</creator><creator>Huguenin-Dumittan, Kevin K</creator><creator>Honarmand, Melika</creator><creator>Xu, Qianjun</creator><creator>Rumiantsev, Egor</creator><creator>Wei Bin How</creator><creator>Langer, Marcel F</creator><creator>Ceriotti, Michele</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20241204</creationdate><title>Fast and flexible range-separated models for atomistic machine learning</title><author>Loche, Philip ; Huguenin-Dumittan, Kevin K ; Honarmand, Melika ; Xu, Qianjun ; Rumiantsev, Egor ; Wei Bin How ; Langer, Marcel F ; Ceriotti, Michele</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_31412566723</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Algorithms</topic><topic>Availability</topic><topic>Electrostatics</topic><topic>Machine learning</topic><topic>Molecular dynamics</topic><toplevel>online_resources</toplevel><creatorcontrib>Loche, Philip</creatorcontrib><creatorcontrib>Huguenin-Dumittan, Kevin K</creatorcontrib><creatorcontrib>Honarmand, Melika</creatorcontrib><creatorcontrib>Xu, Qianjun</creatorcontrib><creatorcontrib>Rumiantsev, Egor</creatorcontrib><creatorcontrib>Wei Bin How</creatorcontrib><creatorcontrib>Langer, Marcel F</creatorcontrib><creatorcontrib>Ceriotti, Michele</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Loche, Philip</au><au>Huguenin-Dumittan, Kevin K</au><au>Honarmand, Melika</au><au>Xu, Qianjun</au><au>Rumiantsev, Egor</au><au>Wei Bin How</au><au>Langer, Marcel F</au><au>Ceriotti, Michele</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Fast and flexible range-separated models for atomistic machine learning</atitle><jtitle>arXiv.org</jtitle><date>2024-12-04</date><risdate>2024</risdate><eissn>2331-8422</eissn><abstract>Most atomistic machine learning (ML) models rely on a locality ansatz, and decompose the energy into a sum of short-ranged, atom-centered contributions. This leads to clear limitations when trying to describe problems that are dominated by long-range physical effects - most notably electrostatics. Many approaches have been proposed to overcome these limitations, but efforts to make them efficient and widely available are hampered by the need to incorporate an ad hoc implementation of methods to treat long-range interactions. We develop a framework aiming to bring some of the established algorithms to evaluate non-bonded interactions - including Ewald summation, classical particle-mesh Ewald (PME), and particle-particle/particle-mesh (P3M) Ewald - into atomistic ML. We provide a reference implementation for PyTorch as well as an experimental one for JAX. Beyond Coulomb and more general long-range potentials, we introduce purified descriptors which disregard the immediate neighborhood of each atom, and are more suitable for general long-ranged ML applications. Our implementations are fast, feature-rich, and modular: They provide an accurate evaluation of physical long-range forces that can be used in the construction of (semi)empirical baseline potentials; they exploit the availability of automatic differentiation to seamlessly combine long-range models with conventional, local ML schemes; and they are sufficiently flexible to implement more complex architectures that use physical interactions as building blocks. We benchmark and demonstrate our torch-pme and jax-pme libraries to perform molecular dynamics simulations, to train range-separated ML potentials, and to evaluate long-range equivariant descriptors of atomic structures.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | EISSN: 2331-8422 |
ispartof | arXiv.org, 2024-12 |
issn | 2331-8422 |
language | eng |
recordid | cdi_proquest_journals_3141256672 |
source | Freely Accessible Journals |
subjects | Algorithms Availability Electrostatics Machine learning Molecular dynamics |
title | Fast and flexible range-separated models for atomistic machine learning |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-08T15%3A27%3A48IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Fast%20and%20flexible%20range-separated%20models%20for%20atomistic%20machine%20learning&rft.jtitle=arXiv.org&rft.au=Loche,%20Philip&rft.date=2024-12-04&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E3141256672%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3141256672&rft_id=info:pmid/&rfr_iscdi=true |