Uncertainty sampling optimizes an equivalent loss, enabling sample complexity analysis and asymptotic superiority guarantees over passive learning in binary classification.
For the SVM-based methods, both the loss and the uncertainty function can be expressed as a function of Y· ˆY , where ˆY =θ⊤X
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2023 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Understanding Uncertainty Sampling via Equivalent Loss
Uncertainty sampling optimizes an equivalent loss, enabling sample complexity analysis and asymptotic superiority guarantees over passive learning in binary classification.