{
  "abstract": "We revisit Breiman's observation that reducing inter-tree correlation without weakening individual trees can improve random forests. Building on this principle, we introduce two variants: Dirichlet-Multinomial Bagging Random Forest (DM) and Dirichlet-Weighted Random Forest (DW). Both modulate sample reweighting via a concentration parameter $α>0$. We provide a simple theoretical criterion that clarifies when these variants behave indistinguishably from standard random forests, and we use it to guide a lightweight tuning strategy. In a controlled evaluation on public classification benchmarks, DM and DW are consistently competitive and often stronger than other random-forest (RF) baselines, with negligible additional runtime.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.21454",
  "author_total": 2,
  "authors": [
    {
      "name": "Quoc Viet Le"
    },
    {
      "name": "Joonha Park"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/5mytv19hbvbb4.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.21454",
  "fulltext_url": null,
  "id": "5mytv19hbvbb4",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.21454",
  "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",
      "stat.ME"
    ],
    [
      "arxiv",
      "stat.ML"
    ],
    [
      "openalex",
      "1702|Machine Learning and Data Classification"
    ]
  ],
  "openalex": "W7213905680",
  "pdf_url": "https://arxiv.org/pdf/2609.21454",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-18",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/5mytv19hbvbb4.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:23:12Z",
      "native_id": "2609.21454",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.21454"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ME",
      "subfield": "statistics"
    }
  ],
  "title": "Improving the Predictive Performance of Bootstrap Aggregating by Dirichlet Resampling",
  "title_text": "Improving the Predictive Performance of Bootstrap Aggregating by Dirichlet Resampling",
  "type": "preprint",
  "updated_at": "2026-10-30T12:23:12Z",
  "url": "https://research.draconitic.com/paper/5mytv19hbvbb4",
  "venue": "arXiv",
  "versions": []
}