Learning Halfspaces with the Zero-One Loss: Time-Accuracy Tradeoffs

no code implementations • NeurIPS 2012 • Aharon Birnbaum, Shai S. Shwartz

Given $\alpha,\epsilon$, we study the time complexity required to improperly learn a halfspace with misclassification error rate of at most $(1+\alpha)\, L^*_\gamma + \epsilon$, where $L^*_\gamma$ is the optimal $\gamma$-margin error rate.

PAC learning