Metraipolis › archive › dc_96a33586aa76
Generalized Residual Closure: General Learning Dynamics for Stability-Plasticity Compatibility — arXiv:2609.38911
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.38911
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T13:45:38.738Z
- SHA-256 of the archived text
6d6f0647e660741a1cac5970d50cc5d59c7dc166931314601c0580969cd217a9- Stable URL of this page
https://metraipolis.com/documento/dc_96a33586aa76
How to cite
Generalized Residual Closure: General Learning Dynamics for Stability-Plasticity Compatibility — arXiv:2609.38911 — arXiv (en), https://arxiv.org/abs/2609.38911 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_96a33586aa76 (Metraipolis archive dc_96a33586aa76, sha256 6d6f0647e660741a1cac5970d50cc5d59c7dc166931314601c0580969cd217a9)
BibTeX
@misc{dc96a33586aa76,
title = {Generalized Residual Closure: General Learning Dynamics for Stability-Plasticity Compatibility — arXiv:2609.38911},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.38911},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_96a33586aa76; sha256 6d6f0647e660741a1cac5970d50cc5d59c7dc166931314601c0580969cd217a9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38911. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Learning must acquire new capabilities while preserving both prior responsibilities and the capacity to learn again. We introduce Generalized Residual Closure (GRC), a framework for learning as recursive closure of future-relevant discrepancies: closing a residual establishes the conditions for subsequent prediction, interaction, and learning. Under a complete representation-relation description at a fixed learner-world boundary, persistent internal learning has two primitive modes: Transformation within a representation and revision of the Representation itself. We establish a local tangent decomposition under regularity assumptions and a criterion for when representation revision is necessary. In an affine model, we derive a necessary-and-sufficient condition for stability-plasticity compatibility and the unique solution of a constrained quadratic update problem, which preserves registered old responsibilities while reducing residuals with an effective safe response. We prove that reconstructive semantic protection weakly enlarges the safe-response operator relative to preserving an exact historical realization. Dynamic sufficiency and future-closure viability extend representation adequacy from current prediction to lawful future updating and continued learning. Growth Learning expands the lawful closure domain or lowers optimal closure cost without regression of the registered capability-cost frontier; a conditional commit rule maintains this order. Restricted-sector recoveries and a conditional representation theorem connect the framework to optimization, machine learning, and control. Together, these results organize adaptation, representation revision, and reusable capability within a common account of continued learning. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.38911 — 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 2026-10-07T13:18:10.286Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).