Metraipolis › archive › dc_37ff2948d236

SHPRR: An Algorithm for Pure Exploration under Constrained Regret — arXiv:2610.39837

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.39837
License (as archived)
CC0-1.0
Archived
2026-10-31T06:13:26.429Z
SHA-256 of the archived text
bade076577f6bf6c5ecec829384ed4c428317928313920e171a4fff6ed694eb3
Stable URL of this page
https://metraipolis.com/documento/dc_37ff2948d236

How to cite

SHPRR: An Algorithm for Pure Exploration under Constrained Regret — arXiv:2610.39837 — arXiv (en), https://arxiv.org/abs/2610.39837 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_37ff2948d236 (Metraipolis archive dc_37ff2948d236, sha256 bade076577f6bf6c5ecec829384ed4c428317928313920e171a4fff6ed694eb3)
BibTeX
@misc{dc37ff2948d236,
  title = {SHPRR: An Algorithm for Pure Exploration under Constrained Regret — arXiv:2610.39837},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.39837},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_37ff2948d236; sha256 bade076577f6bf6c5ecec829384ed4c428317928313920e171a4fff6ed694eb3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39837. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Best Arm Identification (BAI) conventionally measures the cost of experimentation by the number of samples collected. In many operational settings, however, the cost of exploration relative to a trusted baseline already in place is equally important. We study BAI under both a fixed sampling horizon and a regret budget. Unlike generic resources considered in constrained pure exploration, regret has a distinctive structure: sampling better arms is less costly relative to the baseline. We theoretically show that the regret cost of exploration decreases across the phases of Sequential Halving, a widely used pure-exploration algorithm. This observation yields improved guarantees on the probability of identifying the best arm and motivates a more effective allocation of the regret budget. We propose Sequential Halving with Proportional Regret Rationing (SHPRR), which front-loads the regret budget to allow more exploration when many arms remain. Experiments on synthetic and real-world instances show that SHPRR improves best-arm identification performance over uniform regret allocation and existing baselines.

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).
Pagina del lavoro: https://arxiv.org/abs/2610.39837 — 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 2026-10-31T06:07:08.737Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).