SPAᴴM: the spectrum of approximated hamiltonian matrices representations


JSON Export

{
  "revision": 5, 
  "created": "2021-12-15T10:34:29.505178+00:00", 
  "updated": "2023-01-05T19:06:12.297145+00:00", 
  "id": "1175", 
  "metadata": {
    "owner": 22, 
    "license_addendum": null, 
    "title": "SPA\u1d34M: the spectrum of approximated hamiltonian matrices representations", 
    "references": [
      {
        "citation": "A. Fabrizio, K. R. Briling, C. Corminboeuf, Preprint, arXiv:2110.13037 (2021)", 
        "type": "Preprint", 
        "url": "https://arxiv.org/abs/2110.13037"
      }, 
      {
        "citation": "A. Fabrizio, K. R. Briling, C. Corminboeuf, Digital Discovery 1, 286-294 (2022)", 
        "type": "Journal reference", 
        "doi": "10.1039/D1DD00050K", 
        "url": "https://pubs.rsc.org/en/content/articlelanding/2022/dd/d1dd00050k"
      }
    ], 
    "mcid": "2021.221", 
    "description": "Physics-inspired molecular representations are the cornerstone of similarity-based learning applied to solve chemical problems. Despite their conceptual and mathematical diversity, this class of descriptors shares a common underlying philosophy: they all rely on the molecular information that determines the form of the electronic Schr\u00f6dinger equation. Existing representations take the most varied forms, from non-linear functions of atom types and positions to atom densities and potential, up to complex quantum chemical objects directly injected into the ML architecture. In this work, we present the Spectrum of Approximated Hamiltonian Matrices (SPA\u1d34M) as an alternative pathway to construct quantum machine learning representations through leveraging the foundation of the electronic Schr\u00f6dinger equation itself: the electronic Hamiltonian. As the Hamiltonian encodes all quantum chemical information at once, SPA\u1d34M representations not only distinguish different molecules and conformations, but also different spin, charge, and electronic states. As a proof of concept, we focus here on efficient SPA\u1d34M representations built from the eigenvalues of a hierarchy of well-established and readily-evaluated \u201cguess\u201d Hamiltonians. These SPA\u1d34M representations are particularly compact and efficient for kernel evaluation and their complexity is independent of the number of different atom types in the database", 
    "version": 1, 
    "id": "1175", 
    "publication_date": "Dec 15, 2021, 13:09:12", 
    "is_last": true, 
    "doi": "10.24435/materialscloud:js-pz", 
    "_files": [
      {
        "description": "Tar ball containing the geometries and the properties of all the datasets included in the manuscript, as well as the SPAHM representation in a binary format (for further details on the structure and the content of the tar ball, see README.txt)", 
        "size": 2895165440, 
        "key": "SPAHM.tar", 
        "checksum": "md5:984e8926967d1ff4f139c78b5dc69644"
      }, 
      {
        "description": "README", 
        "size": 2465, 
        "key": "README.txt", 
        "checksum": "md5:2a589eb66d011d0db37d5fbd346f636d"
      }
    ], 
    "conceptrecid": "1174", 
    "edited_by": 22, 
    "status": "published", 
    "_oai": {
      "id": "oai:materialscloud.org:1175"
    }, 
    "license": "Creative Commons Attribution 4.0 International", 
    "contributors": [
      {
        "email": "alberto.fabrizio@epfl.ch", 
        "givennames": "Alberto", 
        "affiliations": [
          "Institut des Sciences et Ing\u00e9nierie Chimiques, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL), CH-1015 Lausanne, Switzerland"
        ], 
        "familyname": "Fabrizio"
      }, 
      {
        "givennames": "Ksenia R.", 
        "affiliations": [
          "Institut des Sciences et Ing\u00e9nierie Chimiques, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL), CH-1015 Lausanne, Switzerland"
        ], 
        "familyname": "Briling"
      }, 
      {
        "email": "clemence.corminboeuf@epfl.ch", 
        "givennames": "Clemence", 
        "affiliations": [
          "Institut des Sciences et Ing\u00e9nierie Chimiques, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL), CH-1015 Lausanne, Switzerland"
        ], 
        "familyname": "Corminboeuf"
      }
    ], 
    "keywords": [
      "machine learning", 
      "SPAHM", 
      "Guess Hamiltonians", 
      "Molecular Representation", 
      "EPFL", 
      "MARVEL/DD1", 
      "SNSF", 
      "ERC"
    ]
  }
}