POO is an adaptive algorithm that optimizes noisy black-box functions with unknown local smoothness and matches the performance of known-smoothness methods up to a sqrt(ln n) factor after n evaluations.
Multi-armed bandits on implicit metric spaces
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
-
Black-box optimization of noisy functions with unknown smoothness
POO is an adaptive algorithm that optimizes noisy black-box functions with unknown local smoothness and matches the performance of known-smoothness methods up to a sqrt(ln n) factor after n evaluations.