• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>IEEE Transactions on Information Theory >Non-Asymptotic Analysis of -Norm Support Vector Machines
【24h】

Non-Asymptotic Analysis of -Norm Support Vector Machines

机译：-范数支持向量机的非渐近分析

获取原文
获取原文并翻译 | 示例
       
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Support vector machines (SVMs) with the -penalty became a standard tool in the analysis of high-dimensional classification problems with sparsity constraints in many applications, including bioinformatics and signal processing. We give non-asymptotic results on the performance of -SVM in identification of sparse classifiers. We show that an -dimensional -sparse classification vector can be (with high probability) well approximated from only Gaussian trials. We derive similar estimates also in the presence of misclassifications and for the so-called doubly regularized SVM, which combines the - and the -penalty. Similar bounds were obtained earlier in the analysis of LASSO and 1-Bit compressed sensing.
机译：具有-penalty的支持向量机（SVM）成为分析在许多应用中具有稀疏性约束的高维分类问题的标准工具，包括生物信息学和信号处理。我们给出了-SVM在稀疏分类器识别中的性能的非渐近结果。我们表明，仅高斯试验可以很好地近似三维稀疏分类向量。在存在错误分类的情况下，对于结合了-和-惩罚的所谓的双正则SVM，我们也得出了类似的估计。在分析LASSO和1位压缩感测时，已经获得了相似的界限。

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