AI & ML
Kernel-based guarantees for nonlinear parametric models in Bayesian optimization
arXiv stat.ML0 views
arXiv:2605.13160v2 Announce Type: replace Abstract: Modern Bayesian optimization and adaptive sampling methods increasingly rely on nonlinear parametric models, such as neural networks, yet theoretical guarantees for such models under adaptive data collection remain limited. Existing analyses largely focus on Gaussian processes, kernel machines, linear models, or linearized neural approximations, leaving a gap between theory and the nonlinear models used in practice. We develop a kernel-based framework for analyzing regularized parametric models trained on adaptively collected data. Our approach uses kernels over the parameter space to induce reproducing kernel Hilbert space structures over the corresponding model class, yielding confidence bounds for models trained with a broad class of regularized losses. We show how these bounds can establish convergence guarantees for approximate Thompson sampling and provide a foundation for analyzing broader likelihood-free Bayesian optimization methods. These results provide a unified route to analyzing nonlinear models in Bayesian optimization and related adaptive optimization settings.
Source:https://arxiv.org/abs/2605.13160PreviousSharp feature-learning transitions and Bayes-optimal neural scaling laws in extensive-width networksNextBatched Stochastic Linear Bandits with 1-Bit Communication Constraints
Related posts
Nvidia Earnings; Office Convergence; OS Wars, AI Edition
0Stratechery
France Is Blaming Iran for the Fridge Cyberattack
0Schneier on Security
Apple iPhone Duo Gets a New Facial Unlock Option With iOS 27.3 Update
0FOSS Bytes
CMM. The cursed language that never really took off.
0dev.to Watercooler

I built a GitHub Action that scores pull requests and never auto-closes them
0dev.to GitHub
I built a Windows app to track Instagram follower and profile changes over time
0dev.to GitHub