On the design and evaluation of generative models in high energy density physics
Abstract Understanding high energy density physics (HEDP) is critical for advancements in fusion energy and astrophysics. The computational demands of the computer models used for HEDP studies have led researchers to explore deep learning methods to enhance simulation efficiency. This paper introduc...
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Communications Physics |
| Online Access: | https://doi.org/10.1038/s42005-024-01912-2 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841544632359452672 |
|---|---|
| author | Ankita Shukla Yamen Mubarka Rushil Anirudh Eugene Kur Derek Mariscal Blagoje Djordjevic Bogdan Kustowski Kelly Swanson Brian Spears Peer-Timo Bremer Tammy Ma Pavan Turaga Jayaraman J. Thiagarajan |
| author_facet | Ankita Shukla Yamen Mubarka Rushil Anirudh Eugene Kur Derek Mariscal Blagoje Djordjevic Bogdan Kustowski Kelly Swanson Brian Spears Peer-Timo Bremer Tammy Ma Pavan Turaga Jayaraman J. Thiagarajan |
| author_sort | Ankita Shukla |
| collection | DOAJ |
| description | Abstract Understanding high energy density physics (HEDP) is critical for advancements in fusion energy and astrophysics. The computational demands of the computer models used for HEDP studies have led researchers to explore deep learning methods to enhance simulation efficiency. This paper introduces HEDP-Gen, a framework for training and evaluating generative models tailored for HEDP. Central to HEDP-Gen is Geom-WAE-a generalized Wasserstein auto-encoder accommodating both Euclidean and non-Euclidean latent spaces. HEDP-Gen establishes a rigorous evaluation standard, assessing not only reconstruction fidelity but also scientific validity, sample diversity, and latent space utility in geodesic interpolation and attribute traversal. A case study using hyperbolic geometry (Poincaréball prior) demonstrates that non-Euclidean priors yield scientifically valid samples and stronger generalization in downstream tasks, advantages often missed by conventional reconstruction metrics. |
| format | Article |
| id | doaj-art-f17a9058941042868689372031caa08c |
| institution | Kabale University |
| issn | 2399-3650 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Communications Physics |
| spelling | doaj-art-f17a9058941042868689372031caa08c2025-01-12T12:26:43ZengNature PortfolioCommunications Physics2399-36502025-01-018111110.1038/s42005-024-01912-2On the design and evaluation of generative models in high energy density physicsAnkita Shukla0Yamen Mubarka1Rushil Anirudh2Eugene Kur3Derek Mariscal4Blagoje Djordjevic5Bogdan Kustowski6Kelly Swanson7Brian Spears8Peer-Timo Bremer9Tammy Ma10Pavan Turaga11Jayaraman J. Thiagarajan12University of NevadaLawrence Livermore National LaboratoryLawrence Livermore National LaboratoryLawrence Livermore National LaboratoryLawrence Livermore National LaboratoryLawrence Livermore National LaboratoryLawrence Livermore National LaboratoryLawrence Livermore National LaboratoryLawrence Livermore National LaboratoryLawrence Livermore National LaboratoryLawrence Livermore National LaboratoryArizona State UniversityLawrence Livermore National LaboratoryAbstract Understanding high energy density physics (HEDP) is critical for advancements in fusion energy and astrophysics. The computational demands of the computer models used for HEDP studies have led researchers to explore deep learning methods to enhance simulation efficiency. This paper introduces HEDP-Gen, a framework for training and evaluating generative models tailored for HEDP. Central to HEDP-Gen is Geom-WAE-a generalized Wasserstein auto-encoder accommodating both Euclidean and non-Euclidean latent spaces. HEDP-Gen establishes a rigorous evaluation standard, assessing not only reconstruction fidelity but also scientific validity, sample diversity, and latent space utility in geodesic interpolation and attribute traversal. A case study using hyperbolic geometry (Poincaréball prior) demonstrates that non-Euclidean priors yield scientifically valid samples and stronger generalization in downstream tasks, advantages often missed by conventional reconstruction metrics.https://doi.org/10.1038/s42005-024-01912-2 |
| spellingShingle | Ankita Shukla Yamen Mubarka Rushil Anirudh Eugene Kur Derek Mariscal Blagoje Djordjevic Bogdan Kustowski Kelly Swanson Brian Spears Peer-Timo Bremer Tammy Ma Pavan Turaga Jayaraman J. Thiagarajan On the design and evaluation of generative models in high energy density physics Communications Physics |
| title | On the design and evaluation of generative models in high energy density physics |
| title_full | On the design and evaluation of generative models in high energy density physics |
| title_fullStr | On the design and evaluation of generative models in high energy density physics |
| title_full_unstemmed | On the design and evaluation of generative models in high energy density physics |
| title_short | On the design and evaluation of generative models in high energy density physics |
| title_sort | on the design and evaluation of generative models in high energy density physics |
| url | https://doi.org/10.1038/s42005-024-01912-2 |
| work_keys_str_mv | AT ankitashukla onthedesignandevaluationofgenerativemodelsinhighenergydensityphysics AT yamenmubarka onthedesignandevaluationofgenerativemodelsinhighenergydensityphysics AT rushilanirudh onthedesignandevaluationofgenerativemodelsinhighenergydensityphysics AT eugenekur onthedesignandevaluationofgenerativemodelsinhighenergydensityphysics AT derekmariscal onthedesignandevaluationofgenerativemodelsinhighenergydensityphysics AT blagojedjordjevic onthedesignandevaluationofgenerativemodelsinhighenergydensityphysics AT bogdankustowski onthedesignandevaluationofgenerativemodelsinhighenergydensityphysics AT kellyswanson onthedesignandevaluationofgenerativemodelsinhighenergydensityphysics AT brianspears onthedesignandevaluationofgenerativemodelsinhighenergydensityphysics AT peertimobremer onthedesignandevaluationofgenerativemodelsinhighenergydensityphysics AT tammyma onthedesignandevaluationofgenerativemodelsinhighenergydensityphysics AT pavanturaga onthedesignandevaluationofgenerativemodelsinhighenergydensityphysics AT jayaramanjthiagarajan onthedesignandevaluationofgenerativemodelsinhighenergydensityphysics |