Reducing the Cost of Quantum Chemical Data By Backpropagating Through Density Functional Theory
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913224907030528 |
|---|---|
| author | Mathiasen, Alexander Helal, Hatem Balanca, Paul Krzywaniak, Adam Parviz, Ali Hvilshøj, Frederik Banaszewski, Blazej Luschi, Carlo Fitzgibbon, Andrew William |
| author_facet | Mathiasen, Alexander Helal, Hatem Balanca, Paul Krzywaniak, Adam Parviz, Ali Hvilshøj, Frederik Banaszewski, Blazej Luschi, Carlo Fitzgibbon, Andrew William |
| contents | Density Functional Theory (DFT) accurately predicts the quantum chemical properties of molecules, but scales as $O(N_{\text{electrons}}^3)$. Schütt et al. (2019) successfully approximate DFT 1000x faster with Neural Networks (NN). Arguably, the biggest problem one faces when scaling to larger molecules is the cost of DFT labels. For example, it took years to create the PCQ dataset (Nakata & Shimazaki, 2017) on which subsequent NNs are trained within a week. DFT labels molecules by minimizing energy $E(\cdot )$ as a "loss function." We bypass dataset creation by directly training NNs with $E(\cdot )$ as a loss function. For comparison, Schütt et al. (2019) spent 626 hours creating a dataset on which they trained their NN for 160h, for a total of 786h; our method achieves comparable performance within 31h. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_04030 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Reducing the Cost of Quantum Chemical Data By Backpropagating Through Density Functional Theory Mathiasen, Alexander Helal, Hatem Balanca, Paul Krzywaniak, Adam Parviz, Ali Hvilshøj, Frederik Banaszewski, Blazej Luschi, Carlo Fitzgibbon, Andrew William Machine Learning Density Functional Theory (DFT) accurately predicts the quantum chemical properties of molecules, but scales as $O(N_{\text{electrons}}^3)$. Schütt et al. (2019) successfully approximate DFT 1000x faster with Neural Networks (NN). Arguably, the biggest problem one faces when scaling to larger molecules is the cost of DFT labels. For example, it took years to create the PCQ dataset (Nakata & Shimazaki, 2017) on which subsequent NNs are trained within a week. DFT labels molecules by minimizing energy $E(\cdot )$ as a "loss function." We bypass dataset creation by directly training NNs with $E(\cdot )$ as a loss function. For comparison, Schütt et al. (2019) spent 626 hours creating a dataset on which they trained their NN for 160h, for a total of 786h; our method achieves comparable performance within 31h. |
| title | Reducing the Cost of Quantum Chemical Data By Backpropagating Through Density Functional Theory |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2402.04030 |