Skip to content
AI News HubLIVE
Original source2 min read

HapBO: Harnessed α-π Bayesian Optimization via Expert Natural Language Priors

Summary

HapBO introduces a method that compiles natural language beliefs from experts or LLMs once into a reusable belief function, applied in Bayesian optimization via a bounded positive multiplier without in-loop LLM calls. Theoretical analysis shows that under Expected Improvement, HapBO preserves the standard simple-regret rate up to a bounded factor even with adversarial beliefs. Evaluated on 40 HPOBench tasks, a synthetic suite, and two real-world applications (cortical neurostimulation and constrained solar design), HapBO achieves the lowest aggregate HPOBench regret and strong real-world performance with zero in-loop token cost.

SourcearXiv Machine LearningAuthor: Jean-S\'ebastien Giroux, Rose Guay Hottin, Marco Bonizzato
HapBO: Harnessed α-π Bayesian Optimization via Expert Natural Language Priors
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 18 Nov 2026]

Title:HapBO: Harnessed $α$-$π$ Bayesian Optimization via Expert Natural Language Priors

View a PDF of the paper titled HapBO: Harnessed $\alpha$-$\pi$ Bayesian Optimization via Expert Natural Language Priors, by Jean-S\'ebastien Giroux and 2 other authors

View PDF HTML (experimental)

Abstract:Bayesian Optimization (BO) can be substantially more sample-efficient when informed by prior knowledge about the problem. In practice, however, such knowledge is often available only in natural language, e.g., expert intuitions or documentation, rather than as the explicit probability distribution landscape that prior-guided BO methods may require. Leveraging it effectively demands both an expressive mapping from language to priors and robustness to information that may be misleading. We propose HapBO (Harnessed $\alpha$-$\pi$ Bayesian Optimization), which elicits beliefs once from a human expert, a large language model (LLM), or both, and deterministically compiles a structured specification into a reusable belief function ($\pi: \mathcal{X} \to[0,1]$), with a rich representation not restricted to a Gaussian family. Building on $\alpha$-$\pi$BO, HapBO applies this belief function through a bounded positive multiplier on any nonnegative acquisition, preserving positive acquisition support and requiring no LLM calls during optimization. We prove that, for the Expected Improvement acquisition function (EI), HapBO preserves the standard simple-regret rate up to a bounded factor, even under adversarial beliefs. We evaluate HapBO on 40 HPOBench tasks, a synthetic suite in 6-15 dimensions and two real-world applications: cortical neurostimulation and constrained solar design. HapBO achieves the lowest aggregate HPOBench regret and strong real-world task performance, with zero in-loop token cost. In real-world applications it improves the optimization outcome even at budgets of 12-20 queries, and at a small fraction of the wall-clock and token costs of other LLM-based methods.

Comments: 41 pages, 22 figures, 8 tables. Code: this https URL

Subjects:

Machine Learning (cs.LG); Machine Learning (stat.ML)

ACM classes: I.2.6; G.1.6

Cite as: arXiv:2611.25100 [cs.LG]

(or arXiv:2611.25100v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2611.25100

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Marco Bonizzato [view email] [v1] Wed, 18 Nov 2026 19:36:28 UTC (2,357 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled HapBO: Harnessed $\alpha$-$\pi$ Bayesian Optimization via Expert Natural Language Priors, by Jean-S\'ebastien Giroux and 2 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.LG

new | recent | 2026-11

Change to browse by:

cs stat stat.ML

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

IArxiv recommender toggle

IArxiv Recommender (What is IArxiv?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

InvestorsAdvanced

Key points

  • HapBO compiles natural language priors into a belief function once, eliminating LLM calls during optimization.
  • A bounded positive multiplier applies the belief to any nonnegative acquisition while preserving positive acquisition support.
  • Theoretically preserves the standard simple-regret rate for EI up to a bounded factor, even under adversarial beliefs.
  • Achieves lowest aggregate regret on 40 HPOBench tasks and improves real-world outcomes at 12-20 query budgets.

Highlights and analysis are generated automatically and may contain errors. Check the original source.