Derives an explicit volume-dependent lower bound on regret for GP bandits on Riemannian manifolds that matches the exponent of known upper bounds and includes a new geometric constant.
Gaussian process optimization in the bandit setting: no regret and experimental design
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
eess.SP 2years
2026 2roles
background 1polarities
background 1representative citing papers
A Kronecker-factorized intrinsic Matérn kernel renders GP-UCB tractable on RIS spaces with up to 10^90 configurations while an online marginal-likelihood adaptive window controller matches hand-tuned performance across speeds without per-deployment calibration.
citing papers explorer
-
Manifold-Aware Information Gain and Lower Bounds for Gaussian-Process Bandits on Riemannian Quotient Spaces
Derives an explicit volume-dependent lower bound on regret for GP bandits on Riemannian manifolds that matches the exponent of known upper bounds and includes a new geometric constant.
-
Geometry-Aware Multi-Armed Bandits for Antenna Beam Selection on Spheres, Tori, $\SO(3)$, and Reconfigurable Intelligent Surfaces
A Kronecker-factorized intrinsic Matérn kernel renders GP-UCB tractable on RIS spaces with up to 10^90 configurations while an online marginal-likelihood adaptive window controller matches hand-tuned performance across speeds without per-deployment calibration.