{
  "abstract": "Efficient preconditioning plays an important role in large-scale first-order optimization. In this paper, we propose an adaptive accelerated optimistic dual averaging ($\\text{A}^2$ODA) method for unconstrained convex optimization that adopts low-cost preconditioning based on $p$-norm geometry for $p\\in[2,\\infty]$. The method is line-search-free and employs a new stepsize selection technique based on an aggregated affine lower model. Its update structure is simple and unified across $p\\in[2,\\infty]$, with the case $p>2$ requiring no more elaborate updates than the Euclidean case $p=2$. Under a generalized local smoothness condition, we derive a convergence bound that separates the effects of constant and gap-dependent curvature, with the latter potentially yielding faster-decaying terms. In the special case of local smoothness, this bound recovers a nearly optimal convergence rate.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2611.05334",
  "author_total": 3,
  "authors": [
    {
      "name": "Bowen Li"
    },
    {
      "name": "Danqing Zhou"
    },
    {
      "name": "Chuan He"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/d9trg5gwb86va.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2611.05334",
  "fulltext_url": null,
  "id": "d9trg5gwb86va",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2611.05334",
  "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.AI"
    ],
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "math.OC"
    ],
    [
      "arxiv",
      "stat.ML"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://arxiv.org/pdf/2611.05334",
  "pmcid": null,
  "pmid": null,
  "published": "2026-11-03",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/d9trg5gwb86va.ris",
  "sources": [
    {
      "first_seen": "2026-11-04T15:21:29Z",
      "native_id": "2611.05334",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2611.05334"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:math.OC",
      "subfield": "optimisation-control"
    },
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "A simple adaptive accelerated optimistic dual averaging method for unconstrained convex optimization in $p$-norm geometry",
  "title_text": "A simple adaptive accelerated optimistic dual averaging method for unconstrained convex optimization in p-norm geometry",
  "type": "preprint",
  "updated_at": "2026-11-06T18:21:10Z",
  "url": "https://research.draconitic.com/paper/d9trg5gwb86va",
  "venue": "arXiv",
  "versions": []
}