A no-regret procedure for safe online logistic classification that meets a target error rate with high probability using only O(sqrt(T)) excess tests over an oracle.
Worst-case analysis of selective sampling for linear classification.Journal of Machine Learning Research, 7(7)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
The Good, the Bad, and the Sampled: a No-Regret Approach to Safe Online Classification
A no-regret procedure for safe online logistic classification that meets a target error rate with high probability using only O(sqrt(T)) excess tests over an oracle.