General halfspaces under Gaussian marginals cannot be actively learned with poly(d/ε) unlabeled data unless exponentially many samples are available, but membership queries achieve O~(min{1/p,1/ε}+d polylog(1/ε)) complexity.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Active Learning of General Halfspaces: Label Queries vs Membership Queries
General halfspaces under Gaussian marginals cannot be actively learned with poly(d/ε) unlabeled data unless exponentially many samples are available, but membership queries achieve O~(min{1/p,1/ε}+d polylog(1/ε)) complexity.