Skip to content
AI News HubLIVE
Original source2 min read

No-Regret Bayesian Optimization with Finite-Library Input-Warped Kernels

Summary

The paper introduces FLIWBO, which selects input warps from a finite library of smooth maps via any history-dependent rule while retaining high-probability convergence guarantees for GP-UCB. Experiments show gains over raw-coordinate GP-UCB under geometry misspecification, trap escape, and hyperparameter optimization, plus feasibility in a 20-dimensional multi-agent design study.

SourcearXiv Machine LearningAuthor: Edvin Ketabati Augustinsson, Robert A. Bridges
No-Regret Bayesian Optimization with Finite-Library Input-Warped Kernels
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 2 Sep 2026]

Title:No-Regret Bayesian Optimization with Finite-Library Input-Warped Kernels

View a PDF of the paper titled No-Regret Bayesian Optimization with Finite-Library Input-Warped Kernels, by Edvin Ketabati Augustinsson and 1 other authors

View PDF HTML (experimental)

Abstract:Gaussian-process Bayesian optimization (GP-BO) excels at black-box optimization of costly functions, e.g., hyperparameter optimization (HPO) and multi-agent system (MAS) design. Convergence-rate guarantees exist for select methods, notably GP upper confidence bound (GP-UCB), but require a fixed kernel. Critically, the kernel encodes how input proximity affects objective value similarity. When raw coordinates poorly match this geometry - as with log-scaled hyperparameters or localized peaks - input warping can greatly improve sample efficiency, yet known GP-UCB proofs require a fixed kernel. We propose Finite-Library Input-Warped Bayesian Optimization (FLIWBO), which selects warps from a finite library of smooth input maps by any history-dependent rule. It adapts the input geometry to accelerate learning while retaining high-probability convergence guarantees under mild hypotheses, with an explicit $\sqrt(N_\varepsilon)$ library-size cost. Controlled diagnostics show that finite-library warping repairs planted geometry mismatches and identify FLIWBO failure cases. Across four repeated benchmarks - warped synthetic objectives, a confidence-fence trap, and Fashion-MNIST HPO - FLIWBO-UCB beats raw-coordinate GP-UCB under misspecified geometry, escapes traps that defeat even oracle-warp expected improvement, and recovers much of the gain from manual log scaling, while leading the tested methods that admit a matching regret guarantee. A 20-dimensional MAS design study further shows feasibility under costly noisy evaluations. Code for experiments is available: this https URL.

Subjects:

Machine Learning (cs.LG); Optimization and Control (math.OC); Machine Learning (stat.ML)

Cite as: arXiv:2609.02993 [cs.LG]

(or arXiv:2609.02993v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2609.02993

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Robert Bridges [view email] [v1] Wed, 2 Sep 2026 16:04:07 UTC (8,184 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled No-Regret Bayesian Optimization with Finite-Library Input-Warped Kernels, by Edvin Ketabati Augustinsson and 1 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.LG

new | recent | 2026-09

Change to browse by:

cs math math.OC stat stat.ML

References & Citations

NASA ADS

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

  • FLIWBO allows arbitrary history-dependent warp selection from a finite library with an explicit √(N_ε) library-size cost in the convergence guarantee
  • On warped synthetic objectives, a confidence-fence trap, and Fashion-MNIST HPO, FLIWBO-UCB beats raw-coordinate GP-UCB and escapes traps that defeat oracle-warp expected improvement
  • A 20-dimensional multi-agent system design study demonstrates feasibility under costly noisy evaluations; experiment code is released

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