Metraipolis › archive › dc_cfb4bb87a9df

Meta-Frieren: Beyond Single Level Online Learning — arXiv:2611.07169

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.07169
License (as archived): CC0-1.0
Archived: 2026-11-06T14:44:07.497Z
SHA-256 of the archived text: 058c905a641a9dd9eb1d95c2699c6203fc33a7c1c3876fdc07f5e83203e7cf61
Stable URL of this page: https://metraipolis.com/documento/dc_cfb4bb87a9df

How to cite

Meta-Frieren: Beyond Single Level Online Learning — arXiv:2611.07169 — arXiv (en), https://arxiv.org/abs/2611.07169 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cfb4bb87a9df (Metraipolis archive dc_cfb4bb87a9df, sha256 058c905a641a9dd9eb1d95c2699c6203fc33a7c1c3876fdc07f5e83203e7cf61)

BibTeX

@misc{dccfb4bb87a9df,
  title = {Meta-Frieren: Beyond Single Level Online Learning — arXiv:2611.07169},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.07169},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cfb4bb87a9df; sha256 058c905a641a9dd9eb1d95c2699c6203fc33a7c1c3876fdc07f5e83203e7cf61},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.07169. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study a two-stage online optimization problem: at each round, a meta-learner first selects an agent-environment pair, then the chosen agent interacts with the environment, and receives a reward. We introduce Meta-Frieren, a general framework for maximizing cumulative reward in this setting. Our analysis yields a simple UCB-style criterion for meta-level selection and recovers prior guarantees as special cases while extending them to broader settings. We instantiate Meta-Frieren with GP-UCB under Bayesian and frequentist assumptions. We also derive, to our knowledge, the first high-probability regret bound for Feel-Good Thompson Sampling, specialize it to finite and parametric function classes, and integrate it into Meta-Frieren. Experiments support our theoretical results and demonstrate that Meta-Frieren can be successfully applied to hyperparameter optimization across multiple model classes.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.07169 — 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 2026-11-06T14:21:42.615Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).