Under Gaussian noise, GP prediction error is bounded by a constant multiple of the posterior standard deviation, yielding improved cumulative regret rates for GP-UCB and GP-TS in the frequentist setting.
Hyperparam- eter optimization for machine learning models based on baye sian optimization
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
cs.LG 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
On Improved Regret Bounds In Bayesian Optimization with Gaussian Noise
Under Gaussian noise, GP prediction error is bounded by a constant multiple of the posterior standard deviation, yielding improved cumulative regret rates for GP-UCB and GP-TS in the frequentist setting.