Metraipolis › archive › dc_d685bef0ad0a
Contextual Decision Making: Predictive or Generative — arXiv:2610.32584
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.32584
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-26T20:12:20.414Z
- SHA-256 of the archived text
d3b55ae4bbb08ea17380d2e53375dd0c001b77927ee7581636e3acea096baedc- Stable URL of this page
https://metraipolis.com/documento/dc_d685bef0ad0a
How to cite
Contextual Decision Making: Predictive or Generative — arXiv:2610.32584 — arXiv (en), https://arxiv.org/abs/2610.32584 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d685bef0ad0a (Metraipolis archive dc_d685bef0ad0a, sha256 d3b55ae4bbb08ea17380d2e53375dd0c001b77927ee7581636e3acea096baedc)
BibTeX
@misc{dcd685bef0ad0a,
title = {Contextual Decision Making: Predictive or Generative — arXiv:2610.32584},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.32584},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d685bef0ad0a; sha256 d3b55ae4bbb08ea17380d2e53375dd0c001b77927ee7581636e3acea096baedc},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.32584. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Contextual decision making uses observed covariates to guide decisions under uncertainty. Two natural approaches are predict-then-optimize (PtO), which learns the conditional expected objective, and generate-then-optimize (GtO), which learns conditional uncertainty and optimizes using generated scenarios. We study when each approach is preferable by examining how the choice of learning target affects statistical accuracy and optimization tractability. Although PtO learns a narrower target, our regret bounds show how differences in smoothness can offset GtO's additional dimensional burden. Exploiting smoothness also raises an optimization tradeoff: within the class of nonnegative-weight PtO methods studied, a lower bound limits the gains from additional smoothness, while more flexible methods may introduce signed weights and lose the guarantee of preserving convexity. GtO preserves scenario-wise convexity, but requires learning a richer object and generating scenarios for optimization. Synthetic experiments and a real case study illustrate how these tradeoffs vary with data availability and problem structure. Together with the scope for reusing a model across tasks, our findings provide practical guidance for choosing between the approaches without identifying a universal winner. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Optimization and Control (math.OC); Machine Learning (stat.ML). Pagina del lavoro: https://arxiv.org/abs/2610.32584 — 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 2026-10-26T19:49:03.415Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).