Linear programming with online learning

详细信息	查看全文 | 推荐本文 |

• 作者：Tatsiana Levina ; Yuri Levin ; Jeff McGill ; Mikhail Nediak
• 关键词：Linear programming ; Online learning ; Aggregating algorithm
• 刊名：Operations Research Letters
• 出版年：2007
• 期刊代码：134_01676377
• 类别：et
• 出版时间：September 2007
• 卷：35
• 期：5
• 页码：612-618
• 文件大小：162 K

摘要

We propose online decision strategies for time-dependent sequences of linear programs which use no distributional and minimal geometric assumptions about the data. These strategies are obtained through Vovk's aggregating algorithm which combines recommendations from a given strategy pool. We establish an average-performance bound for the resulting solution sequence.