Metraipolis › archive › dc_5cc20b14879c
Data Reuse in Non-Stationary Learning — arXiv:2610.10340
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.10340
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T12:37:32.414Z
- SHA-256 of the archived text
3d42bc957e22dc61f0fe9a0ba41922c2b5ac764094a24897568bd7f6de460f44- Stable URL of this page
https://metraipolis.com/documento/dc_5cc20b14879c
How to cite
Data Reuse in Non-Stationary Learning — arXiv:2610.10340 — arXiv (en), https://arxiv.org/abs/2610.10340 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5cc20b14879c (Metraipolis archive dc_5cc20b14879c, sha256 3d42bc957e22dc61f0fe9a0ba41922c2b5ac764094a24897568bd7f6de460f44)
BibTeX
@misc{dc5cc20b14879c,
title = {Data Reuse in Non-Stationary Learning — arXiv:2610.10340},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.10340},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5cc20b14879c; sha256 3d42bc957e22dc61f0fe9a0ba41922c2b5ac764094a24897568bd7f6de460f44},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10340. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We consider online learning in non-stationary environments, where the goal is to track an unknown parameter that switches abruptly between a finite set of recurring values. Recurrence opens the possibility of judiciously reusing past observations to improve algorithm performance. However, the changing nature of the underlying signal and lack of information on these dynamics may limit the ability to "safely" reuse data. In this paper we quantify some of the fundamental tradeoffs in this class of problems, and show that they bear a certain resemblance to the classical bias-variance dilemma. Specifically, we propose a class of anytime algorithms, dubbed Exposure-Capped Reuse (ECR), that combine online change detection, compatibility testing, and "contamination" control. We characterize the regime in which ECR's regret scales with the number of distinct values rather than the number of changes, and derive a novel information-theoretic lower bound that establishes the near-minimax optimality of ECR. This provides rigorous quantification of the statistical "value" of data reuse. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.10340 — 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 2026-10-08T12:14:15.464Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).