An ab initio foundation model of wavefunctions that accurately describes chemical bond breaking
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908420813094912 |
|---|---|
| author | Foster, Adam Schätzle, Zeno Szabó, P. Bernát Cheng, Lixue Köhler, Jonas Cassella, Gino Gao, Nicholas Li, Jiawei Noé, Frank Hermann, Jan |
| author_facet | Foster, Adam Schätzle, Zeno Szabó, P. Bernát Cheng, Lixue Köhler, Jonas Cassella, Gino Gao, Nicholas Li, Jiawei Noé, Frank Hermann, Jan |
| contents | Reliable description of bond breaking remains a major challenge for quantum chemistry due to the multireferential character of the electronic structure in dissociating species. Multireferential methods in particular suffer from large computational cost, which under the normal paradigm has to be paid anew for each system at a full price, ignoring commonalities in electronic structure across molecules. Quantum Monte Carlo with deep neural networks (deep QMC) uniquely offers to exploit such commonalities by pretraining transferable wavefunction models, but all such attempts were so far limited in scope. Here, we bring this new paradigm to fruition with Orbformer, a novel transferable wavefunction model pretrained on 22,000 equilibrium and dissociating structures that can be fine-tuned on unseen molecules reaching an accuracy-cost ratio rivalling classical multireferential methods. On established benchmarks as well as more challenging bond dissociations and Diels-Alder reactions, Orbformer is the only method that consistently converges to chemical accuracy (1 kcal/mol). This work turns the idea of amortizing the cost of solving the Schrödinger equation over many molecules into a practical approach in quantum chemistry. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_19960 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | An ab initio foundation model of wavefunctions that accurately describes chemical bond breaking Foster, Adam Schätzle, Zeno Szabó, P. Bernát Cheng, Lixue Köhler, Jonas Cassella, Gino Gao, Nicholas Li, Jiawei Noé, Frank Hermann, Jan Chemical Physics Artificial Intelligence Machine Learning Reliable description of bond breaking remains a major challenge for quantum chemistry due to the multireferential character of the electronic structure in dissociating species. Multireferential methods in particular suffer from large computational cost, which under the normal paradigm has to be paid anew for each system at a full price, ignoring commonalities in electronic structure across molecules. Quantum Monte Carlo with deep neural networks (deep QMC) uniquely offers to exploit such commonalities by pretraining transferable wavefunction models, but all such attempts were so far limited in scope. Here, we bring this new paradigm to fruition with Orbformer, a novel transferable wavefunction model pretrained on 22,000 equilibrium and dissociating structures that can be fine-tuned on unseen molecules reaching an accuracy-cost ratio rivalling classical multireferential methods. On established benchmarks as well as more challenging bond dissociations and Diels-Alder reactions, Orbformer is the only method that consistently converges to chemical accuracy (1 kcal/mol). This work turns the idea of amortizing the cost of solving the Schrödinger equation over many molecules into a practical approach in quantum chemistry. |
| title | An ab initio foundation model of wavefunctions that accurately describes chemical bond breaking |
| topic | Chemical Physics Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2506.19960 |