{
  "abstract": "We study the gradient query complexity of sampling from a density $π(x)\\propto\\mathrm{e}^{-V(x)}$ on $\\mathbb{R}^d$, where $V$ has a $β$-Lipschitz gradient but need not be convex. Our approach uses the proximal sampler, which alternates Gaussian perturbation with sampling a position conditional on the noisy observation. We implement its observation chain using the high-order noisy conditional sampler of [OpenAI 2026], obtaining improved dimension dependence under functional inequalities. If $π$ satisfies a log-Sobolev inequality (LSI) with constant $α$, then for every fixed $ν>0$, there is a finite constant $C_ν$ depending only on $ν$ such that the algorithm returns a sample within total-variation distance $\\varepsilon$ using at most $C_νκ(d+κ+\\varepsilon^{-1}+\\|\\nabla V(x_0)\\|^2/β)^ν$ queries, where $κ=β/α$ and $x_0$ is an arbitrary reference point for initialization. The analysis controls center-dependent local errors along exact proximal histories and removes the final observation noise by conditional decoding. Under a Poincaré inequality (PI), we obtain a corresponding guarantee from a warm start with a known bound on its Rényi divergence. An oracle lower bound shows that a stationary point alone, which suffices under LSI, is insufficient under PI.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2611.03442",
  "author_total": 6,
  "authors": [
    {
      "name": "Wei Guo"
    },
    {
      "name": "Bo Yuan"
    },
    {
      "name": "Ye He"
    },
    {
      "name": "Jiaming Liang"
    },
    {
      "name": "Molei Tao"
    },
    {
      "name": "Yongxin Chen"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/2h8eqq07h3w2k.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2611.03442",
  "fulltext_url": null,
  "id": "2h8eqq07h3w2k",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2611.03442",
  "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.CC"
    ],
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "math.ST"
    ],
    [
      "arxiv",
      "stat.ML"
    ],
    [
      "arxiv",
      "stat.TH"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://arxiv.org/pdf/2611.03442",
  "pmcid": null,
  "pmid": null,
  "published": "2026-11-02",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/2h8eqq07h3w2k.ris",
  "sources": [
    {
      "first_seen": "2026-11-03T12:21:14Z",
      "native_id": "2611.03442",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2611.03442"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:math.ST",
      "subfield": "statistics"
    }
  ],
  "title": "Subpolynomial-Query Proximal Sampling Beyond Log-Concavity",
  "title_text": "Subpolynomial-Query Proximal Sampling Beyond Log-Concavity",
  "type": "preprint",
  "updated_at": "2026-11-05T15:20:35Z",
  "url": "https://research.draconitic.com/paper/2h8eqq07h3w2k",
  "venue": "arXiv",
  "versions": []
}