{
  "abstract": "Accelerating the prediction of long-term behavior in chaotic systems is crucial in scientific computing. However, existing methods rely on numerical solvers or autoregressive models that advance one small step at a time, which makes long horizons expensive. We instead view this problem as learning the system's time-invariant evolution operator, which jumps the state across a large time span in a single evaluation. To this end, we derive the consistency equations a time-invariant operator must satisfy, with differential and compositional objectives in physical time. These equations also connect the learned operator to the physics-prescribed instant dynamics, enabling physics embedding in consistency learning. Across five chaotic systems, we find that physics-distilled consistency makes both short-term trajectories and long-term statistics more accurate. The learned operator survives temporal extrapolation and requires one-tenth as many evaluations as autoregressive rollout, offering an efficient route to long-term simulation of chaotic dynamics.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.04108",
  "author_total": 4,
  "authors": [
    {
      "name": "Lufang Chiang"
    },
    {
      "name": "Jiachen Yao"
    },
    {
      "name": "Thomas Y. L. Lin"
    },
    {
      "name": "Anima Anandkumar"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/0yjs7yt2z2rdc.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.04108",
  "fulltext_url": null,
  "id": "0yjs7yt2z2rdc",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.04108",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "nlin.CD"
    ],
    [
      "openalex",
      "3109|Model Reduction and Neural Networks"
    ]
  ],
  "openalex": "W7220680319",
  "pdf_url": "https://arxiv.org/pdf/2610.04108",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-20",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/0yjs7yt2z2rdc.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:34:18Z",
      "native_id": "2610.04108",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.04108"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:nlin.CD",
      "subfield": "statistical-nonlinear"
    }
  ],
  "title": "Physics is the Best Teacher: Consistency Learning for Time-Invariant Operators of Chaotic Dynamics",
  "title_text": "Physics is the Best Teacher: Consistency Learning for Time-Invariant Operators of Chaotic Dynamics",
  "type": "preprint",
  "updated_at": "2026-10-30T12:34:18Z",
  "url": "https://research.draconitic.com/paper/0yjs7yt2z2rdc",
  "venue": "arXiv",
  "versions": []
}