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.
Optimal rates of convergence for nonparametric estima- tors,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
eess.SP 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
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.