Metraipolis › archive › dc_b01cbfa79bfe

Implicit Assumptions About Tasks in Continual Learning — arXiv:2610.41792

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.41792
License (as archived): CC0-1.0
Archived: 2026-11-03T07:53:12.055Z
SHA-256 of the archived text: c555fcc880416473c56761abc0b4eb37c88f4db8f093c62421612fae9618a6eb
Stable URL of this page: https://metraipolis.com/documento/dc_b01cbfa79bfe

How to cite

Implicit Assumptions About Tasks in Continual Learning — arXiv:2610.41792 — arXiv (en), https://arxiv.org/abs/2610.41792 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b01cbfa79bfe (Metraipolis archive dc_b01cbfa79bfe, sha256 c555fcc880416473c56761abc0b4eb37c88f4db8f093c62421612fae9618a6eb)

BibTeX

@misc{dcb01cbfa79bfe,
  title = {Implicit Assumptions About Tasks in Continual Learning — arXiv:2610.41792},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41792},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b01cbfa79bfe; sha256 c555fcc880416473c56761abc0b4eb37c88f4db8f093c62421612fae9618a6eb},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41792. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Continual learning is the study of how a model accumulates knowledge from data received over time, rather than all at once. In practice, this is typically achieved by dividing a dataset into tasks and presenting them sequentially. Explanations of the resulting measurements take into account factors such as the similarity between segments, the rate at which the data changes and the order of presentation. Each of these factors can be defined in terms of the underlying data, the partition imposed on it, or the learner that encounters it. These levels do not necessarily coincide, and it is usually left implicit which level a reported quantity refers to. We separate these and identify which properties acquire a value at each level. In controlled teacher--student experiments, we demonstrate that partitioning the same underlying trajectory at different levels of granularity, changing the order of presentation, and varying the similarity structure of the underlying data all result in different measured outcomes. We review representative benchmarks to determine which of these properties are stated. Where the underlying data cannot be inspected, as in foundation models built on undisclosed pre-training corpora, its properties are inherited by the model's initial state, and the training applied on top of it can be described.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.41792 — 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 2026-11-03T07:49:31.173Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).