{
  "abstract": "Simulation-based inference with neural posterior estimation (NPE) often yields overconfident and unreliable posteriors under limited simulation budgets. To address this, we propose DRO-NPE, a distributionally robust approach that replaces the standard NPE objective with a worst-case loss over a Wasserstein ambiguity set. We introduce KL-based metrics for miscoverage and miscalibration, and use these to show that the DRO-NPE objective controls overfitting and reduces posterior overconfidence. Our method is tractable, parallelisable, and readily integrates with standard normalising flows. Across benchmark SBI tasks, DRO-NPE consistently improves coverage and calibration, while narrowing the gap between empirical and population NPE loss, leading to more reliable inference in low-simulation regimes.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2605.28516",
  "author_total": 5,
  "authors": [
    {
      "name": "William Laplante"
    },
    {
      "name": "Yuga Hikida"
    },
    {
      "name": "Charita Dellaporta"
    },
    {
      "name": "François-Xavier Briol"
    },
    {
      "name": "Ayush Bharti"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/7y0y16xkpwnn2.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2605.28516",
  "fulltext_url": null,
  "id": "7y0y16xkpwnn2",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2605.28516",
  "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",
      "2613|Markov Chains and Monte Carlo Methods"
    ]
  ],
  "openalex": "W7162666264",
  "pdf_url": "https://arxiv.org/pdf/2605.28516",
  "pmcid": null,
  "pmid": null,
  "published": "2026-11-04",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/7y0y16xkpwnn2.ris",
  "sources": [
    {
      "first_seen": "2026-11-05T15:21:06Z",
      "native_id": "2605.28516",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2605.28516"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "Conservative neural posterior estimation via distributionally robust training",
  "title_text": "Conservative neural posterior estimation via distributionally robust training",
  "type": "preprint",
  "updated_at": "2026-11-09T00:20:31Z",
  "url": "https://research.draconitic.com/paper/7y0y16xkpwnn2",
  "venue": "arXiv",
  "versions": []
}