{
  "abstract": "Recent frameworks in differential privacy (DP), such as privacy loss distributions and $f$-DP, provide lossless representations of the privacy leakage of mechanisms. These approaches are often considered to yield tighter $(\\varepsilon, δ)$-DP guarantees than those obtained from relaxed notions such as Rényi DP. But is that always the case? We study this question for differentially private stochastic gradient descent (DP-SGD) with fixed-size batches under replace adjacency. Our key observation is that in this setting, privacy accounting based on Rényi DP can use a pair of worst-case distributions (i.e., a dominating pair) that differs from the one used in the lossless frameworks. In particular, we characterize the worst-case distributions as two-dimensional Gaussian mixtures and derive an improved Rényi DP bound for DP-SGD. Numerical and asymptotic comparisons show that across various hyperparameter settings, a Rényi DP accountant based on the new bound can yield better privacy guarantees than those obtained from the lossless frameworks.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.17120",
  "author_total": 1,
  "authors": [
    {
      "name": "Jinho Bok"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/6m6v46hdnh3v8.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.17120",
  "fulltext_url": null,
  "id": "6m6v46hdnh3v8",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.17120",
  "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.CR"
    ],
    [
      "arxiv",
      "cs.DS"
    ],
    [
      "arxiv",
      "cs.IT"
    ],
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "math.IT"
    ],
    [
      "arxiv",
      "stat.ML"
    ],
    [
      "openalex",
      "1702|Privacy-Preserving Technologies in Data"
    ]
  ],
  "openalex": "W7221785798",
  "pdf_url": "https://arxiv.org/pdf/2610.17120",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-12",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/6m6v46hdnh3v8.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:29:19Z",
      "native_id": "2610.17120",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.17120"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "Can Rényi Accountants Beat Lossless Accountants for DP-SGD?",
  "title_text": "Can Rényi Accountants Beat Lossless Accountants for DP-SGD?",
  "type": "preprint",
  "updated_at": "2026-10-30T12:29:26Z",
  "url": "https://research.draconitic.com/paper/6m6v46hdnh3v8",
  "venue": "arXiv",
  "versions": []
}