Variational Monte Carlo approach to partial differential equations with neural networks
The accurate numerical solution of partial differential equations (PDEs) is a central task in numerical analysis allowing to model a wide range of natural phenomena by employing specialized solvers depending on the scenario of application. Here, we develop a variational approach for solving PDEs gov...
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Dokumenttyp: | Article (Journal) Editorial |
| Sprache: | Englisch |
| Veröffentlicht: |
1 December 2022
|
| In: |
Machine learning: science and technology
Year: 2022, Jahrgang: 3, Heft: 4, Pages: 1-7 |
| ISSN: | 2632-2153 |
| DOI: | 10.1088/2632-2153/aca317 |
| Online-Zugang: | Verlag, kostenfrei, Volltext: https://doi.org/10.1088/2632-2153/aca317 Verlag, kostenfrei, Volltext: https://iopscience.iop.org/article/10.1088/2632-2153/aca317 
|
| Verfasserangaben: | Moritz Reh and Martin Gärttner |
MARC
| LEADER | 00000caa a2200000 c 4500 | ||
|---|---|---|---|
| 001 | 1831329972 | ||
| 003 | DE-627 | ||
| 005 | 20231108100300.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 230118s2022 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1088/2632-2153/aca317 |2 doi | |
| 035 | |a (DE-627)1831329972 | ||
| 035 | |a (DE-599)KXP1831329972 | ||
| 035 | |a (OCoLC)1389536265 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rda | ||
| 041 | |a eng | ||
| 084 | |a 29 |2 sdnb | ||
| 100 | 1 | |a Reh, Moritz |d 1995- |e VerfasserIn |0 (DE-588)1247844358 |0 (DE-627)1782431616 |4 aut | |
| 245 | 1 | 0 | |a Variational Monte Carlo approach to partial differential equations with neural networks |c Moritz Reh and Martin Gärttner |
| 264 | 1 | |c 1 December 2022 | |
| 300 | |b Diagramme | ||
| 300 | |a 7 | ||
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Gesehen am 08.11.2023 | ||
| 520 | |a The accurate numerical solution of partial differential equations (PDEs) is a central task in numerical analysis allowing to model a wide range of natural phenomena by employing specialized solvers depending on the scenario of application. Here, we develop a variational approach for solving PDEs governing the evolution of high dimensional probability distributions. Our approach naturally works on the unbounded continuous domain and encodes the full probability density function through its variational parameters, which are adapted dynamically during the evolution to optimally reflect the dynamics of the density. In contrast to previous works, this dynamical adaptation of the parameters is carried out using an explicit prescription avoiding iterative gradient descent. For the considered benchmark cases we observe excellent agreement with numerical solutions as well as analytical solutions for tasks that are challenging for traditional computational approaches. | ||
| 700 | 1 | |a Gärttner, Martin |d 1985- |e VerfasserIn |0 (DE-588)1047469529 |0 (DE-627)778426076 |0 (DE-576)401083527 |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Machine learning: science and technology |d Bristol : IOP Publishing, 2020 |g 3(2022), 4, Artikel-ID 04LT02, Seite 1-7 |h Online-Ressource |w (DE-627)1694891836 |w (DE-600)3017004-7 |x 2632-2153 |7 nnas |a Variational Monte Carlo approach to partial differential equations with neural networks |
| 773 | 1 | 8 | |g volume:3 |g year:2022 |g number:4 |g elocationid:04LT02 |g pages:1-7 |g extent:7 |a Variational Monte Carlo approach to partial differential equations with neural networks |
| 856 | 4 | 0 | |u https://doi.org/10.1088/2632-2153/aca317 |x Verlag |x Resolving-System |z kostenfrei |3 Volltext |
| 856 | 4 | 0 | |u https://iopscience.iop.org/article/10.1088/2632-2153/aca317 |x Verlag |z kostenfrei |3 Volltext |
| 951 | |a AR | ||
| 992 | |a 20230118 | ||
| 993 | |a Editorial | ||
| 994 | |a 2022 | ||
| 998 | |g 1047469529 |a Gärttner, Martin |m 1047469529:Gärttner, Martin |d 130000 |d 130000 |d 130200 |d 700000 |d 728500 |e 130000PG1047469529 |e 130000PG1047469529 |e 130200PG1047469529 |e 700000PG1047469529 |e 728500PG1047469529 |k 0/130000/ |k 0/130000/ |k 1/130000/130200/ |k 0/700000/ |k 1/700000/728500/ |p 2 |y j | ||
| 998 | |g 1247844358 |a Reh, Moritz |m 1247844358:Reh, Moritz |d 130000 |d 130700 |d 700000 |d 728500 |e 130000PR1247844358 |e 130700PR1247844358 |e 700000PR1247844358 |e 728500PR1247844358 |k 0/130000/ |k 1/130000/130700/ |k 0/700000/ |k 1/700000/728500/ |p 1 |x j | ||
| 999 | |a KXP-PPN1831329972 |e 4249387127 | ||
| BIB | |a Y | ||
| SER | |a journal | ||
| JSO | |a {"origin":[{"dateIssuedKey":"2022","dateIssuedDisp":"1 December 2022"}],"name":{"displayForm":["Moritz Reh and Martin Gärttner"]},"relHost":[{"type":{"media":"Online-Ressource","bibl":"periodical"},"part":{"volume":"3","pages":"1-7","year":"2022","text":"3(2022), 4, Artikel-ID 04LT02, Seite 1-7","extent":"7","issue":"4"},"note":["Gesehen am 17. April 2020"],"title":[{"title":"Machine learning: science and technology","title_sort":"Machine learning: science and technology"}],"origin":[{"publisher":"IOP Publishing","dateIssuedDisp":"2020-","publisherPlace":"Bristol","dateIssuedKey":"2020"}],"recId":"1694891836","pubHistory":["Volume 1, number 1 (1 March 2020)-"],"disp":"Variational Monte Carlo approach to partial differential equations with neural networksMachine learning: science and technology","id":{"doi":["10.1088/2632-2153"],"issn":["2632-2153"],"zdb":["3017004-7"],"eki":["1694891836"]},"language":["eng"],"physDesc":[{"extent":"Online-Ressource"}]}],"recId":"1831329972","language":["eng"],"id":{"doi":["10.1088/2632-2153/aca317"],"eki":["1831329972"]},"physDesc":[{"noteIll":"Diagramme","extent":"7 S."}],"type":{"media":"Online-Ressource","bibl":"article-journal"},"note":["Gesehen am 08.11.2023"],"title":[{"title":"Variational Monte Carlo approach to partial differential equations with neural networks","title_sort":"Variational Monte Carlo approach to partial differential equations with neural networks"}],"person":[{"role":"aut","given":"Moritz","roleDisplay":"VerfasserIn","display":"Reh, Moritz","family":"Reh"},{"role":"aut","given":"Martin","roleDisplay":"VerfasserIn","display":"Gärttner, Martin","family":"Gärttner"}]} | ||
| SRT | |a REHMORITZGVARIATIONA1202 | ||