A tighter maximum posterior variance bound gives near-optimal cumulative and simple regret guarantees for GP bandits in noiseless, large-norm, and non-stationary-noise settings.
On kernelized multi-armed bandits
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Improved Regret Analysis in Gaussian Process Bandits: Optimality for Noiseless Reward, RKHS norm, and Non-Stationary Variance
A tighter maximum posterior variance bound gives near-optimal cumulative and simple regret guarantees for GP bandits in noiseless, large-norm, and non-stationary-noise settings.