Metraipolis › archive › dc_0b9673aebedb

In-Context Batch Black-box Optimization via Flow Matching — arXiv:2610.20138

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.20138
License (as archived)
CC0-1.0
Archived
2026-10-15T14:19:40.851Z
SHA-256 of the archived text
c8b15cded331be0c0dbe8578d5c5aa440b2f81e0290c55020645765103681f9b
Stable URL of this page
https://metraipolis.com/documento/dc_0b9673aebedb

How to cite

In-Context Batch Black-box Optimization via Flow Matching — arXiv:2610.20138 — arXiv (en), https://arxiv.org/abs/2610.20138 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0b9673aebedb (Metraipolis archive dc_0b9673aebedb, sha256 c8b15cded331be0c0dbe8578d5c5aa440b2f81e0290c55020645765103681f9b)
BibTeX
@misc{dc0b9673aebedb,
  title = {In-Context Batch Black-box Optimization via Flow Matching — arXiv:2610.20138},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.20138},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0b9673aebedb; sha256 c8b15cded331be0c0dbe8578d5c5aa440b2f81e0290c55020645765103681f9b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.20138. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Batch black-box optimization is important for expensive systems where many candidates can be evaluated in parallel, yet only a few rounds of evaluation are affordable. In this regime, effective batch construction must identify multiple promising regions while avoiding redundant evaluations, and conventional Bayesian optimization can require increasingly difficult batch-selection procedures as the batch size grows. We introduce Flow Matching for Thompson-Sampling Refinement (FMTR), an amortized approach that learns offline a continuous, history-conditioned proposal distribution from which variable-size batches can be sampled. FMTR is trained offline by conditional flow matching on Thompson-sampling argmaxes refined toward high-value regions via a horizon-dependent Langevin pushforward map, adapting the exploration-exploitation tradeoff over the optimization horizon. At test time, the model parameters remain fixed and batch generation requires neither task-specific surrogate refitting nor numerical acquisition optimization. FMTR achieves strong performance against batch BO and in-context baselines on synthetic and real-world benchmarks, while substantially reducing the computational cost of batch selection.

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/2610.20138 — 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 2026-10-15T13:53:35.705Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).