Metraipolis › archive › dc_4f8977e986de

Beyond Class Marginals: Bounding Rehearsal Gaps without Freezing Class Co-occurrence — arXiv:2609.25735

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.25735
License (as archived)
CC0-1.0
Archived
2026-10-08T13:46:37.508Z
SHA-256 of the archived text
a06038c71eaeeb08c6867459f5df73b0e60c2c3612d5b473d4c4e68aa032e212
Stable URL of this page
https://metraipolis.com/documento/dc_4f8977e986de

How to cite

Beyond Class Marginals: Bounding Rehearsal Gaps without Freezing Class Co-occurrence — arXiv:2609.25735 — arXiv (en), https://arxiv.org/abs/2609.25735 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4f8977e986de (Metraipolis archive dc_4f8977e986de, sha256 a06038c71eaeeb08c6867459f5df73b0e60c2c3612d5b473d4c4e68aa032e212)
BibTeX
@misc{dc4f8977e986de,
  title = {Beyond Class Marginals: Bounding Rehearsal Gaps without Freezing Class Co-occurrence — arXiv:2609.25735},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.25735},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4f8977e986de; sha256 a06038c71eaeeb08c6867459f5df73b0e60c2c3612d5b473d4c4e68aa032e212},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.25735. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-23 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2609.25735 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T13:18:38.256Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).