The paper introduces Finite-Library Input-Warped Bayesian Optimization (FLIWBO), a method that selects input warps from a finite library to adapt the geometry used by Gaussian‑process Bayesian optimization. FLIWBO maintains high‑probability convergence guarantees while improving sample efficiency on problems where raw coordinates poorly match the objective’s geometry, such as log‑scaled hyperparameters or localized peaks. Experiments on synthetic benchmarks, Fashion‑MNIST hyperparameter tuning, and a 20‑dimensional multi‑agent system design demonstrate that FLIWBO‑UCB outperforms raw‑coordinate GP‑UCB and other methods with regret guarantees, especially under misspecified geometry.
By Edvin Ketabati Augustinsson, Robert A. Bridges
arXiv:2607. 04356v1 Announce Type: new Abstract: Bayesian Optimization (BO) generally begins with an initialization phase: a batch of $n_0$ uninformed evaluations.
By Mujin Cheon, James Odgers, Dong-Yeun Koh, Calvin Tsay
arXiv:2603. 09276v2 Announce Type: replace-cross Abstract: We study a widely used Bayesian optimization method, Gaussian process Thompson sampling (GP-TS), under the assumption that the objective function is a sample path from a GP.
By Shion Takeno, Shogo Iwazaki
arXiv:2608. 18863v1 Announce Type: cross Abstract: We study Bayesian optimization in a time-varying environment where the unknown reward function evolves according to a Gaussian process drift model.
By Matthias Mandl, Hanne Kekkonen
The paper investigates how fast predictive regret guarantees of exact Bayesian online learning can be maintained when using approximate posterior methods. It establishes a general theorem linking the cumulative cost of posterior approximation to the contraction radius of the exact Gibbs posterior and the Wasserstein distance between approximate and exact posteriors. Three concrete online learning scenarios—linear models, infinite‑dimensional exponential families, and Gaussian process regression—illustrate that appropriately accurate approximations (projected Langevin, truncation, and sparse variational posteriors) preserve fast regret bounds while reducing computational demands.
By Ilsang Ohn
arXiv:2512. 00517v3 Announce Type: replace-cross Abstract: Sequential optimization of black-box functions from noisy evaluations has been widely studied, with Gaussian Process bandit algorithms such as GP-UCB guaranteeing no-regret in stationary settings.
By Eliabelle Mauduit, Elo\"ise Berthier, Andrea Simonetto
arXiv:2605. 20145v2 Announce Type: replace-cross Abstract: Gaussian process (GP) predictive distributions are commonly used in Bayesian optimization (BO) to guide the selection of evaluation points for expensive objective functions.
By Aur\'elien Pion, Emmanuel Vazquez
The paper analyzes Bayesian linear bandits with isotropic Gaussian parameters, independent Gaussian arms, and Gaussian reward noise when the time horizon scales with the dimension. It derives explicit limits for the normalized posterior uncertainty and parameter overlaps, yielding exact regret curves for several policies—including Thompson sampling, posterior‑mean greedy selection, and scaled‑covariance variants. The results show that posterior‑mean greedy selection achieves the optimal Bayes regret, while Thompson sampling incurs a strictly larger leading regret whose ratio to greedy lies between one and two, approaching two for long horizons.
By Prakhar Singhvi (Abstract Math Institute), Yi Zou (Abstract Math Institute), Abhishek Bhattacharjee (Abstract Math Institute)
The paper introduces Online Hyperparameter Optimization (OHPO), framing it as an infinitely many‑armed bandit problem over mixed and conditional search spaces. It proposes the IMABO framework, which couples any bandit policy with any oracle for proposing new configurations, and presents IMOSS—a restart‑free anytime policy with provable regret bounds. Experiments show that IMABO, combined with practical oracles such as TPE, an incumbent‑mutation oracle, and a pretrained tabular foundation model, outperforms random search across a range of settings from classical ML models to LLM‑based agents.
By Louis Abraham, Tuan-Anh Nguyen, Nicolas Devatine
arXiv:2610.01269v1 Announce Type: cross
Abstract: Bayesian Optimisation (BO) is a powerful framework for the optimisation of expensive black-box functions, but typically requires refitting a surrogat...
By Luca Geminiani, Nadja Klein
arXiv:2511.20413v2 Announce Type: replace-cross
Abstract: \emph{Decision-focused learning} (DFL) trains predictive models to optimize downstream decisions rather than prediction accuracy alone. While...
By Zhuojun Xie, Adam Abdin, Yiping Fang
arXiv:2603. 08287v2 Announce Type: replace-cross Abstract: We analyze the Bayesian regret of the Gaussian process posterior sampling reinforcement learning (GP-PSRL) algorithm.
By Hamish Flynn, Joe Watson, Ingmar Posner, Jan Peters