Active Learning for Classification with Abstention
ISIT(2020)
摘要
We consider the problem of binary classification with the caveat that the learner can abstain from declaring a label incurring a cost λ ∈ [0,1/2] in the process. This is referred to as the problem of binary classification with a fixed-cost of abstention. For this problem, we propose an active learning strategy that constructs a non-uniform partition of the input space and focuses sampling in the regions near the decision boundaries. Our proposed algorithm can work in all the commonly used active learning query models, namely membership-query, pool-based and stream-based. We obtain an upper bound on the excess risk of our proposed algorithm under standard smoothness and margin assumptions and demonstrate its minimax near-optimality by deriving a matching (modulo poly-logarithmic factors) lower bound. The achieved minimax rates are always faster than the corresponding rates in the passive setting, and furthermore the improvement increases with larger values of the smoothness and margin parameters.
更多查看译文
关键词
Information theory,Standards,Medical diagnostic imaging,Euclidean distance,Adaptation models,Risk management,Regression tree analysis
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络