{
  "abstract": "Estimating neural scaling laws involves an end-to-end pipeline: designing a scaling recipe, training models across scales, evaluating models on a target metric, and deploying an algorithm to fit a scaling law to the resulting data. This final fitting stage is often treated as routine: standard procedures minimize a non-convex fitting loss using local optimization from a grid of initializations, and return the best solution found. Yet such heuristic searches can fail in two distinct ways: they offer no guarantee of returning a nearly optimal solution, and they obscure whether fundamentally different parameter choices fit the data nearly as well. Indeed, we show that standard scaling law fitting is subject to a Rashomon effect (Breiman, 2001): the sublevel sets of near-minimizers correspond to broad parameter regions whose extrapolations diverge substantially at scale. We resolve these issues with a deterministic branch-and-bound algorithm that guarantees nearly optimal fitting loss and exhaustively maps the near-minimizers to the implied range of scaling curves.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.34514",
  "author_total": 2,
  "authors": [
    {
      "name": "Bruno Mlodozeniec"
    },
    {
      "name": "Spencer Frei"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/9bmzr5fp9wtf4.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.34514",
  "fulltext_url": null,
  "id": "9bmzr5fp9wtf4",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.34514",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "stat.ML"
    ],
    [
      "openalex",
      "1702|Stochastic Gradient Optimization Techniques"
    ]
  ],
  "openalex": "W7223984944",
  "pdf_url": "https://arxiv.org/pdf/2610.34514",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-25",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/9bmzr5fp9wtf4.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:35:49Z",
      "native_id": "2610.34514",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.34514"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "Ambiguous Fits: The Rashomon Effect and Challenges in Scaling Law Estimation",
  "title_text": "Ambiguous Fits: The Rashomon Effect and Challenges in Scaling Law Estimation",
  "type": "preprint",
  "updated_at": "2026-10-30T12:35:49Z",
  "url": "https://research.draconitic.com/paper/9bmzr5fp9wtf4",
  "venue": "arXiv",
  "versions": []
}