Metraipolis › archive › dc_31d3784ccccf
When Is Coarse Supervision Worth It? Cost-Aware Learning under Unknown Aggregation — arXiv:2609.36704
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.36704
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T17:29:23.621Z
- SHA-256 of the archived text
21c6bcebda6207b74718e9743f59126f7e7d78422821478852cd44da52f7e371- Stable URL of this page
https://metraipolis.com/documento/dc_31d3784ccccf
How to cite
When Is Coarse Supervision Worth It? Cost-Aware Learning under Unknown Aggregation — arXiv:2609.36704 — arXiv (en), https://arxiv.org/abs/2609.36704 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_31d3784ccccf (Metraipolis archive dc_31d3784ccccf, sha256 21c6bcebda6207b74718e9743f59126f7e7d78422821478852cd44da52f7e371)
BibTeX
@misc{dc31d3784ccccf,
title = {When Is Coarse Supervision Worth It? Cost-Aware Learning under Unknown Aggregation — arXiv:2609.36704},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.36704},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_31d3784ccccf; sha256 21c6bcebda6207b74718e9743f59126f7e7d78422821478852cd44da52f7e371},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36704. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Modern learning systems often acquire supervision at multiple resolutions, trading annotation cost against information content. We study cost-aware two-resolution learning, where expensive fine labels reveal a vector response and cheaper coarse labels reveal a scalar aggregate formed with unknown weights, while the target remains the full response. The challenge is that unknown aggregation changes which directions coarse data can identify, so the value of coarse supervision depends jointly on cost, noise, and identification. We characterize this information geometry and develop an estimate-and-track policy that learns the aggregation rule and tracks the optimal resolution mix. We derive a closed-form break-even condition for coarse supervision and prove that the online policy attains the optimal leading cumulative-risk coefficient, with a matching local asymptotic minimax lower bound. Synthetic experiments support the predicted all-fine/mixed transition, show the online learner approaching the oracle-share benchmark, and demonstrate a finite-budget gain over all-fine acquisition when coarse supervision is sufficiently favorable. Our results provide a principled way to balance information and annotation cost across supervision resolutions. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.LG). Categorie arXiv: Machine Learning (cs.LG) ; Machine Learning (stat.ML). Pagina del lavoro: https://arxiv.org/abs/2609.36704 — 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 2026-10-07T16:59:48.223Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).