Metraipolis › archive › dc_782bc262d989
Robust Satisficing Ensemble: Scalable Model Aggregation Under Distribution Shifts — arXiv:2611.10895
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.10895
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-10T18:42:55.251Z
- SHA-256 of the archived text
8b5508155b82755809e5fdf151f4a293388118800a4ff2dbd58e352fe4fb408f- Stable URL of this page
https://metraipolis.com/documento/dc_782bc262d989
How to cite
Robust Satisficing Ensemble: Scalable Model Aggregation Under Distribution Shifts — arXiv:2611.10895 — arXiv (en), https://arxiv.org/abs/2611.10895 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_782bc262d989 (Metraipolis archive dc_782bc262d989, sha256 8b5508155b82755809e5fdf151f4a293388118800a4ff2dbd58e352fe4fb408f)
BibTeX
@misc{dc782bc262d989,
title = {Robust Satisficing Ensemble: Scalable Model Aggregation Under Distribution Shifts — arXiv:2611.10895},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.10895},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_782bc262d989; sha256 8b5508155b82755809e5fdf151f4a293388118800a4ff2dbd58e352fe4fb408f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.10895. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Standard ensemble methods can improve robustness by mitigating individual model stochasticity, but they frequently fail to generalize beyond the training distribution, leaving systems vulnerable to out-of-distribution (OOD) data. We introduce the Robust Satisficing Ensemble (RSE), a scalable probabilistic aggregation framework designed to secure model combinations by minimizing their fragility against distributional changes. By bridging a robust satisficing objective with a quadratic risk surrogate, RSE derives an analytical inner adversary. This fundamental reformulation enables highly efficient weight updates without the computational bottleneck of standard minimax optimization, crucially decoupling optimization complexity from sample size to scale effectively to large datasets. In particular, we prove a geometrically decaying truncation error for the fragility approximation via Lagrange-Burmann expansion and establish stationarity guarantees for RSE. We evaluate RSE across a comprehensive spectrum of distribution shifts, including adversarial label shift (SST-5, TREC), natural subpopulation and temporal shifts (CivilComments, HuffPost). Our results demonstrate that RSE consistently outperforms strong robust baselines, including GroupDRO, IRM, and SRM. These findings establish RSE as a practical, theoretically grounded safeguard for reliable model aggregation in dynamic environments. 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); Machine Learning (stat.ML). Pagina del lavoro: https://arxiv.org/abs/2611.10895 — 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 2026-11-10T18:37:37.614Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).