{
  "abstract": "Machine learning has transformed materials simulation by delivering force fields with ab initio accuracy, yet bridging the gap between high-dimensional regression and physical interpretability remains a grand challenge. Conventional analytical potentials offer transparency but often fail to capture the complexity of far-from-ground state regimes. Here, we introduce a hybrid symbolic-neural framework that unifies the interpretability of the Embedded Atom Method (EAM) with the adaptability of data-driven learning. Using Equation Learner Neural Networks (EqNNs) trained on density functional theory (DFT) data, we obtain interpretable models for aluminum through three distinct training protocols: random initialization trained via Monte Carlo Tree Search (MCTS) and gradient descent, and two transfer-learning strategies initialized from a copper potential - one employing MCTS followed by gradient descent, and the other using gradient descent only. We find that while all three resulting symbolic models achieve sub-10 meV/atom accuracy, they occupy distinct local minima in the functional landscape, exhibiting complementary trade-offs across phonon dispersion, surface energetics, and elastic response. By integrating these diverse functional forms through a weighted symbolic ensemble, we derive a composite potential that surpasses the fidelity of its constituent models. The resulting ensemble effectively mitigates individual biases, delivering superior consistency with DFT benchmarks across equation-of-state curvature, phonon spectra, and melting dynamics. This approach demonstrates that combining transfer learning with ensemble symbolic regression yields compact, transparent potentials capable of robust prediction across equilibrium and non-equilibrium states.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.16526",
  "author_total": 9,
  "authors": [
    {
      "name": "Bilvin Varughese"
    },
    {
      "name": "Aditya Koneru"
    },
    {
      "name": "Adil Muhammad"
    },
    {
      "name": "Troy D. Loeffler"
    },
    {
      "name": "Sukriti Manna"
    },
    {
      "name": "Jan Michael Y. Carrillo"
    },
    {
      "name": "Orcun Yildiz"
    },
    {
      "name": "Thomas Peterka"
    },
    {
      "name": "Subramanian K. R. S. Sankaranarayanan"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/8q1zg2823wxj3.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.16526",
  "fulltext_url": null,
  "id": "8q1zg2823wxj3",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.16526",
  "language": null,
  "licence": "CC-BY-NC-SA-4.0",
  "licence_label": "CC BY-NC-SA 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cond-mat.mtrl-sci"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://arxiv.org/pdf/2609.16526",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-15",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/8q1zg2823wxj3.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:21:41Z",
      "native_id": "2609.16526",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.16526"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:cond-mat.mtrl-sci",
      "subfield": "condensed-matter"
    }
  ],
  "title": "Symbolic Ensemble Learning Enables Discovery of Fast Accurate Physics-Based Interatomic Potentials",
  "title_text": "Symbolic Ensemble Learning Enables Discovery of Fast Accurate Physics-Based Interatomic Potentials",
  "type": "preprint",
  "updated_at": "2026-10-30T12:21:41Z",
  "url": "https://research.draconitic.com/paper/8q1zg2823wxj3",
  "venue": "arXiv",
  "versions": []
}