Metraipolis › archive › dc_724891490ede

m-Set Adversarial Bandits with Winner Feedback — arXiv:2610.10128

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.10128
License (as archived)
CC0-1.0
Archived
2026-10-08T12:36:05.094Z
SHA-256 of the archived text
afc057b7e333c57ddf32f40546e8755237ad57ffd922c6f3dd26023734649d95
Stable URL of this page
https://metraipolis.com/documento/dc_724891490ede

How to cite

m-Set Adversarial Bandits with Winner Feedback — arXiv:2610.10128 — arXiv (en), https://arxiv.org/abs/2610.10128 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_724891490ede (Metraipolis archive dc_724891490ede, sha256 afc057b7e333c57ddf32f40546e8755237ad57ffd922c6f3dd26023734649d95)
BibTeX
@misc{dc724891490ede,
  title = {m-Set Adversarial Bandits with Winner Feedback — arXiv:2610.10128},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.10128},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_724891490ede; sha256 afc057b7e333c57ddf32f40546e8755237ad57ffd922c6f3dd26023734649d95},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10128. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We show upper and lower bounds on the regret of $m$-set adversarial bandits for different utilities (winner reward or sum of rewards) and feedback models (winner index, winner reward, sum of rewards, and their combinations). By comparing to standard bounds for combinatorial and MNL bandits, our results reveal how subtle changes in the setting can have a dramatic impact on the learning rates. Our main technical contributions are the information-theoretic lower bounds on the regret. Experiments on synthetic data confirm our theoretical analyses.

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/2610.10128 — 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 2026-10-08T12:14:15.304Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).