首页> 外文会议>International conference on algorithmic learning theory >Learning Boolean Halfspaces with Small Weights from Membership Queries
【24h】

Learning Boolean Halfspaces with Small Weights from Membership Queries

机译:从成员查询中学习具有较小权重的布尔半空间

获取原文

摘要

We consider the problem of proper learning a Boolean Half-space with integer weights {0,1,...,t} from membership queries only. The best known algorithm for this problem is an adaptive algorithm that asks n~(O(t~5)) membership queries where the best lower bound for the number of membership queries is n~t. In this paper we close this gap and give an adaptive proper learning algorithm with two rounds that asks n~(O(t5)) membership queries. We also give a non-adaptive proper learning algorithm that asks n~(O(t~3)) membership queries.
机译:我们考虑仅从成员资格查询中适当学习具有整数权重{0,1,...,t}的布尔半空间的问题。针对该问题的最著名算法是自适应算法,该算法询问n〜(O(t〜5))个成员资格查询,其中成员资格查询数量的最佳下限为n〜t。在本文中,我们缩小了这一差距,并给出了两轮询问n〜(O(t5))成员资格查询的自适应适当学习算法。我们还给出了一种非自适应的正确学习算法,该算法会询问n〜(O(t〜3))个成员资格查询。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号