Metraipolis › archive › dc_302ebe07343d

The Surrogate Is Not the Reward: Post-Surrogate Primary-Outcome Acquisition in Contextual Bandits — arXiv:2610.06610

Source
arXiv
Original
https://arxiv.org/abs/2610.06610
License (as archived)
CC0-1.0
Archived
2026-10-06T05:32:32.389Z
SHA-256 of the archived text
a62d464789ebe85bed56fd63a20ea72a6cfcc65672535047fecb5118613ecb50
Stable URL of this page
https://metraipolis.com/documento/dc_302ebe07343d

How to cite

The Surrogate Is Not the Reward: Post-Surrogate Primary-Outcome Acquisition in Contextual Bandits — arXiv:2610.06610 — arXiv, https://arxiv.org/abs/2610.06610 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_302ebe07343d (Metraipolis archive dc_302ebe07343d, sha256 a62d464789ebe85bed56fd63a20ea72a6cfcc65672535047fecb5118613ecb50)
BibTeX
@misc{dc302ebe07343d,
  title = {The Surrogate Is Not the Reward: Post-Surrogate Primary-Outcome Acquisition in Contextual Bandits — arXiv:2610.06610},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.06610},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_302ebe07343d; sha256 a62d464789ebe85bed56fd63a20ea72a6cfcc65672535047fecb5118613ecb50},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.06610. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study contextual bandits in which a surrogate is observed after the action but before the learner decides whether to acquire the primary outcome that defines action value and regret. The value of acquiring the primary outcome depends on both decision relevance (how much the current outcome matters for comparing policies) and the residual uncertainty after observing the surrogate. The Audited Surrogate Bandit (ASB) learns a contextual policy while allocating a budget of $B$ primary-outcome acquisitions over $T$ rounds. ASB sets a pre-surrogate acquisition level from current decision relevance and, after observing the surrogate, redistributes that level using an estimate of that residual uncertainty. For a finite class of $N$ policies over $K$ actions, ASB incurs $\widetilde O[\sqrt{KT\log N}\{1+\sqrt{T/B}\}]$ regret relative to the best policy in the class. In a two-action family where the surrogate does not reveal the better action, a learner that observes the surrogate before deciding whether to acquire can achieve bounded regret, whereas any learner that must decide before seeing the surrogate incurs $\Omega(T/B)$ worst-case regret under the same budget. Synthetic experiments show that both acquisition factors matter: ASB has lower regret than variants using only decision relevance or only residual uncertainty. On a KuaiRec benchmark of user-video interactions, the regret gap relative to relevance-only acquisition widens and then narrows as the budget grows.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.06610 — 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 2026-10-06T05:27:06.041Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).