arXiv:2603. 07965v2 Announce Type: replace-cross Abstract: Bayesian optimization (BO) for high-dimensional constrained problems remains a significant challenge due to the curse of dimensionality.
The paper investigates nonlinear dimensionality reduction for Bayesian optimisation (BO) by transforming high‑dimensional black‑box optimisation problems into a sequence of low‑dimensional latent‑space BO (LSBO) tasks. It extends earlier linear embedding approaches by using variational autoencoders (VAEs), deep metric loss, and adaptive retraining to better capture nonlinear structure, and couples LSBO with sequential domain reduction (SDR‑LSBO) to progressively narrow search domains. Experiments on GPU‑accelerated BoTorch with Matérn‑5/2 Gaussian‑process surrogates show that VAE‑based LSBO outperforms adaptive linear embeddings, and the authors provide a theoretical analysis of latent‑space error versus representation gap under PAC‑Bayes conditions.
arXiv:2603. 09793v2 Announce Type: replace Abstract: Bayesian optimization is a data-efficient technique that has been shown to be extremely powerful to optimize expensive, black-box, and possibly noisy objective functions.
The paper introduces Total Sensitivity Kernels (TSKs), a weighted ANOVA kernel framework that learns the importance of individual inputs and their interactions for approximating a multivariable black-box function from limited data. By selecting an RKHS where the target function has minimum norm, the authors derive a unique solution and prove consistency for finite-data interpolation. Numerical experiments show that adapting the kernel to the learned multivariable structure can significantly improve approximation accuracy compared to a standard product kernel.
arXiv:2608. 04113v1 Announce Type: cross Abstract: Black-box optimization is a ubiquitous problem in science and engineering, often dealing with expensive objective functions with cheaper lower-fidelity proxies available.
The paper introduces a pooling‑ridge estimation method for functional linear regression that handles data observed at discrete times, ranging from sparse to dense designs. By combining pooling strategies with RKHS‑based techniques, the authors achieve minimax‑optimal prediction risk for both scalar‑on‑function and function‑on‑function models. The study identifies distinct phase transitions in convergence behavior, with up to three transitions for function‑on‑function regression, and validates the approach through simulations and real data examples.
The paper explores how to use gradients of simulator outputs with respect to input parameters to improve Bayesian inference for expensive simulators. By incorporating gradient information into Gaussian process surrogate models, the authors show that Bayesian optimization can converge faster under a limited simulation budget. They find that reverse‑mode differentiation yields efficiency gains, while forward‑mode does not offset its computational cost, especially when the number of parameters exceeds the output dimensionality.
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.
arXiv:2608. 12687v1 Announce Type: new Abstract: Bayesian optimization (BO) is a sample-efficient framework for analog circuit topology search, where evaluating each candidate topology can require costly simulation.
arXiv:2511. 16340v2 Announce Type: replace Abstract: Efficient Gaussian process (GP) inference is critical for sequential decision-making tasks such as active learning, online prediction, and Bayesian optimization.
arXiv:2607. 29225v1 Announce Type: new Abstract: Bayesian Optimization (BO) is widely adopted for data-efficient optimization in scientific and engineering applications, yet its computational cost is rarely evaluated alongside optimization performance.
BoLT is a new benchmark designed to make black-box optimization research for large language model (LLM) tasks more accessible. It presents a suite of realistic LLM optimization problems—covering multi‑fidelity, multi‑objective, heteroscedastic noise, and high‑dimensional search spaces—grounded in thousands of real experiments and represented by lightweight surrogate models. The authors evaluate a wide range of Bayesian and other black‑box optimization methods on BoLT, finding that some BO techniques consistently outperform others and revealing gaps in current methods for LLM optimization.