Metraipolis › archive › dc_489cf8cc40c8

Certified Behavioral Retention for Continual Adaptation with Held-Out Anchors — arXiv:2610.40740

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.40740
License (as archived)
CC0-1.0
Archived
2026-11-02T07:49:19.168Z
SHA-256 of the archived text
008c10b72636f26b8172a78acc71be3e7ea73a5f8f32b92cdc21595d0e265927
Stable URL of this page
https://metraipolis.com/documento/dc_489cf8cc40c8

How to cite

Certified Behavioral Retention for Continual Adaptation with Held-Out Anchors — arXiv:2610.40740 — arXiv (en), https://arxiv.org/abs/2610.40740 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_489cf8cc40c8 (Metraipolis archive dc_489cf8cc40c8, sha256 008c10b72636f26b8172a78acc71be3e7ea73a5f8f32b92cdc21595d0e265927)
BibTeX
@misc{dc489cf8cc40c8,
  title = {Certified Behavioral Retention for Continual Adaptation with Held-Out Anchors — arXiv:2610.40740},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.40740},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_489cf8cc40c8; sha256 008c10b72636f26b8172a78acc71be3e7ea73a5f8f32b92cdc21595d0e265927},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40740. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Continual adaptation requires deciding not only how to update a model, but whether to commit an update without exceeding a declared budget for changes to protected behavior. We introduce Certified Anchor-Based Adaptation (CABA), a candidate-agnostic post-update gate that reserves historical observations from candidate optimization, compares old and candidate policies on frozen representations, and selects the largest tested interpolation coefficient whose worst-anchor forward KL divergence remains within budget. The finite check requires neither action labels nor complete trajectories. We develop a theory-led certification framework that separates measured anchor retention from conditional off-anchor guarantees. Under explicit representation-coverage and Lipschitz assumptions, an accepted update satisfies a uniform behavioral-divergence bound on protected support. The analysis gives regularity bounds for affine softmax heads, probabilistic coverage and compression guarantees, interpolation monotonicity conditions, grid-resolution bounds, and trajectory-level and sequential-composition guarantees. In a controlled UCI Human Activity Recognition study used as a non-stationary sensor-policy proxy, CABA reduces mean forgetting from 1.01 percent for unconstrained adaptation to 0.00 percent at budget epsilon = 0.05, while reducing final average accuracy from 93.04 percent to 88.48 percent. The experiment illustrates a retention-plasticity trade-off and does not establish foundation-model or robotic performance. CABA provides an auditable retention check for candidate generators exposing comparable policy distributions and a declared update path, while deployment also requires separate evidence of current-task utility.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2610.40740 — 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 2026-11-02T07:40:00.157Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).