{
  "abstract": "Class-balanced replay controls class frequency but does not determine the interval between successive replay appearances of a class. We study this interval, the rehearsal gap, separately from the class marginal and class co-occurrence, and introduce randomised-pass replay (RPR), which visits each resident class once per shuffled pass. For a fixed set of C resident classes and replay batch size b less than or equal to C, RPR preserves the balanced time-averaged class marginal and bounds every gap by 2*ceil(C/b)-1; a churn-conditional bound applies while the resident set changes. The scheduler uses no future class information and adds no replay examples or forward passes. In a linear-head ER-ACE diagnostic, joint absence from the incoming and replay batches produces a one-sided classifier-bias gradient. Longer absence episodes are associated with larger negative bias displacement, and removing the incoming-loss mask attenuates the scheduling effect. In the primary ER-ACE experiments, RPR improves final average accuracy by 0.72-1.67 percentage points relative to independent class-balanced retrieval under reservoir storage, with positive effects also observed under balanced storage. Pretrained ViTs show positive effects on the tested LT10 streams with small replay batches, while matched larger-batch controls show no material effect. Fixed-cycle and reused-pass controls change more than one temporal statistic, so the experiments do not isolate rehearsal-gap length from all other forms of temporal dependence. The accuracy effects depend on the learner and operating regime.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.25735",
  "author_total": 3,
  "authors": [
    {
      "name": "Congren Dai"
    },
    {
      "name": "Nat Roongjirarat"
    },
    {
      "name": "Fei Ye"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/61df3e71dk1ye.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.25735",
  "fulltext_url": null,
  "id": "61df3e71dk1ye",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.25735",
  "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",
      "stat.ML"
    ],
    [
      "openalex",
      "1702|Domain Adaptation and Few-Shot Learning"
    ]
  ],
  "openalex": "W7214073934",
  "pdf_url": "https://arxiv.org/pdf/2609.25735",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-22",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/61df3e71dk1ye.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:23:49Z",
      "native_id": "2609.25735",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.25735"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "Beyond Class Marginals: Bounding Rehearsal Gaps without Freezing Class Co-occurrence",
  "title_text": "Beyond Class Marginals: Bounding Rehearsal Gaps without Freezing Class Co-occurrence",
  "type": "preprint",
  "updated_at": "2026-10-30T12:23:49Z",
  "url": "https://research.draconitic.com/paper/61df3e71dk1ye",
  "venue": "arXiv",
  "versions": []
}