Metraipolis › archive › dc_4f776dff4e7d

SABLE: Scalable Affine Bayesian Latent-space Exploration — arXiv:2610.31495

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.31495
License (as archived): CC0-1.0
Archived: 2026-10-23T15:16:44.343Z
SHA-256 of the archived text: e46198bd6d736258c416a9fbab403bd7767acffac2377d7bfdf786dd07613cab
Stable URL of this page: https://metraipolis.com/documento/dc_4f776dff4e7d

How to cite

SABLE: Scalable Affine Bayesian Latent-space Exploration — arXiv:2610.31495 — arXiv (en), https://arxiv.org/abs/2610.31495 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4f776dff4e7d (Metraipolis archive dc_4f776dff4e7d, sha256 e46198bd6d736258c416a9fbab403bd7767acffac2377d7bfdf786dd07613cab)

BibTeX

@misc{dc4f776dff4e7d,
  title = {SABLE: Scalable Affine Bayesian Latent-space Exploration — arXiv:2610.31495},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.31495},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4f776dff4e7d; sha256 e46198bd6d736258c416a9fbab403bd7767acffac2377d7bfdf786dd07613cab},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.31495. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Complex objects such as engineering designs and proteins are often difficult to optimise because their design spaces exhibit high-dimensional structure and objective evaluations are expensive. Generative models provide continuous latent representations, but their latent spaces can have thousands to tens of thousands of dimensions, creating a regime where the latent dimension $D$ greatly exceeds the evaluation budget. We introduce SABLE, a Bayesian optimisation method for high-dimensional latent spaces with an isotropic distribution and limited budget. SABLE uses a Bayesian affine surrogate for prediction and acquisition, treating higher-order structure as surrogate discrepancy. After $N$ observations, the slope update has dimension at most $N-1$, yielding a decomposition of each query into an in-span component optimised by expected improvement (EI) in at most $N$ dimensions and an off-span component governed by a scalar norm. We show that the off-span norm implicitly selected by affine EI can lead to underexploration, and SABLE instead prescribes it using a finite-horizon schedule, without restricting search to a learned subspace. A recompression scheme reduces information to $\mathcal O(M)$ pseudo-observations, bounding refitting cost by $\mathcal O(M^2D+M^3)$ while keeping parameter inference, prediction, and acquisition decisions to tens of milliseconds. Across synthetic benchmarks and latent-space optimisation tasks, SABLE achieves high sample efficiency and reduces decision time by several orders of magnitude at large budgets.

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); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2610.31495 — 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 2026-10-23T15:09:08.630Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).