Bayesian Optimization with Fisher Information Geometry: Gradient Bounds and Trust-Region Methods
cs.LG, cs.AI, cs.IT, math.IT
Submitted: 2026-09-25
Updated: 2026-09-25
Comments: Accepted at NeurIPS 2026
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- A Tutorial on Bayesian Optimization
- Vanilla Bayesian Optimization Performs Great in High Dimensions
- Standard Gaussian Process is All You Need for High-Dimensional Bayesian Optimization
- Understanding High-Dimensional Bayesian Optimization
- We Still Don't Understand High-Dimensional Bayesian Optimization
- Position: Why We Must Rethink Empirical Research in Machine Learning
- A Study of Bayesian Neural Network Surrogates for Bayesian Optimization
- The reparameterization trick for acquisition functions
- Learning Riemannian Manifolds for Geodesic Motion Skills
- GIT-BO: High-Dimensional Bayesian Optimization with Tabular Foundation Models
- Metrics for Probabilistic Geometries
- Latent Space Oddity: on the Curvature of Deep Generative Models
- Pulling back information geometry
- Riemann$^2$: Learning Riemannian Submanifolds from Riemannian Data
- Notes on Kullback-Leibler Divergence and Likelihood
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks