Metraipolis › archive › dc_0f858b32dd67

Online Adaptive Kernel Mixing for Gaussian Process Decision Making — arXiv:2609.19891

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.19891
License (as archived): CC0-1.0
Archived: 2026-10-10T04:08:47.760Z
SHA-256 of the archived text: bb59a70434ddf98c19cf336b01a43e5ddfec590bb4a5befa44344e14eae344da
Stable URL of this page: https://metraipolis.com/documento/dc_0f858b32dd67

How to cite

Online Adaptive Kernel Mixing for Gaussian Process Decision Making — arXiv:2609.19891 — arXiv (en), https://arxiv.org/abs/2609.19891 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0f858b32dd67 (Metraipolis archive dc_0f858b32dd67, sha256 bb59a70434ddf98c19cf336b01a43e5ddfec590bb4a5befa44344e14eae344da)

BibTeX

@misc{dc0f858b32dd67,
  title = {Online Adaptive Kernel Mixing for Gaussian Process Decision Making — arXiv:2609.19891},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.19891},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0f858b32dd67; sha256 bb59a70434ddf98c19cf336b01a43e5ddfec590bb4a5befa44344e14eae344da},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.19891. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Gaussian Processes (GPs) are widely used as surrogates for black-box functions in sequential decision-making problems such as Bayesian optimization (BO), level set estimation (LSE), and Bayesian active learning (BAL). GP performance critically depends on kernels, and standard kernels can lead to suboptimal decisions under misspecification. To address this, we introduce HACK GPs (Hedge Adaptive Cumulative Kernels), a method that views kernel selection as an online learning with expert advice problem. HACK treats each candidate kernel as a GP "expert" and updates a distribution over experts online using AdaHedge, based on a loss received as a proxy for their ability to fit the function and align with the task objective. We provide two variants of HACK: (i) Mixture of Gaussians (MoG) and (ii) categorical sampling. We establish general guarantees showing that, under a loss-gap condition, the weight concentrates on the best kernel and the resulting acquisition function is close to that of the best expert. Empirically, we observe robust performance across BO, LSE, and BAL compared to standard kernels such as Squared Exponential and Matern-5/2, as well as simple ensemble baselines.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-18 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.19891 — 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 2026-10-10T03:48:18.299Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).