Exponential Savings in Agnostic Active Learning through Abstention

高效主动学习与回避

Efficient Active Learning with Abstention

本文提出了一种高效的主动学习算法，允许在困难样本上回避预测，从而显著降低标签复杂性，同时避免噪声寻求行为。

不可知成员查询学习中的非平凡节省：新结果与技术

Agnostic Membership Query Learning with Nontrivial Savings: New Results, Techniques

本研究提出在不可知学习模型下，针对两类电路（门为亚对数次数多项式阈值函数或亚指数大小亚对数次数对称电路）的成员查询学习算法，实现时间2^{n-s(n)}（s(n)≈n/(k+1)）的非平凡节省，超越平凡运行时间2^n。

Revisiting Model-Agnostic Private Learning: Faster Rates and Active Learning

The Private Aggregation of Teacher Ensembles (PATE) framework is one of the most promising recent approaches in differentially private learning. Existing theoretical analysis shows that PATE consistently learns any VC-classes in the realizable setting, but falls short in explaining its success in more general cases where the error rate of the optimal classifier is bounded away from zero. We fill in this gap by introducing the Tsybakov Noise Condition (TNC) and establish stronger and more interpretable learning bounds. These bounds provide new insights into when PATE works and improve over exis…