Kometo achieves near-optimal simple regret in multi-fidelity optimization of locally smooth functions without knowledge of smoothness or cost-bias parameters.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Adaptive multi-fidelity optimization with fast learning rates
Kometo achieves near-optimal simple regret in multi-fidelity optimization of locally smooth functions without knowledge of smoothness or cost-bias parameters.