在线学习与再生核Hilbert空间的竞争On-line learning competitive with reproducing kernel Hilbert spaces |
|
课程网址: | http://videolectures.net/mcslw04_vovk_llcrk/ |
主讲教师: | Vladimir Vovk |
开课单位: | 伦敦大学学院 |
开课时间: | 2007-02-25 |
课程语种: | 英语 |
中文简介: | 在本次演讲中,我将描述一种新技术,用于设计有竞争力的在线预测算法并证明它们的损失范围。 这种算法的目标是在广泛的基准类中执行几乎与最佳决策规则一样好,而不对假设的生成方式做出假设。 但是,该领域的标准算法只能处理有限维(通常可数)的基准类。 新技术为无限维函数空间的决策规则提供了类似的结果。 它基于最近的概率基础的博弈论方法,更具体地说,基于最近关于防御性预测的结果。 给定由防御性预测算法产生的概率,其已知被很好地校准并且在长期内具有良好的分辨率,预期的损失最小化原理用于找到合适的预测。 |
课程简介: | In this talk I will describe a new technique for designing competitive on-line prediction algorithms and proving loss bounds for them. The goal of such algorithms is to perform almost as well as the best decision rules in a wide benchmark class, with no assumptions made about the way the observations are generated. However, standard algorithms in this area can only deal with finite-dimensional (often countable) benchmark classes. The new technique gives similar results for decision rules ranging over infinite-dimensional function spaces. It is based on a recent game-theoretic approach to the foundations of probability and, more specifically, on recent results about defensive forecasting. Given the probabilities produced by a defensive forecasting algorithm, which are known to be well calibrated and to have good resolution in the long run, the expected loss minimization principle is used to find a suitable prediction. |
关 键 词: | 在线预测算法; 无限维函数空间; 博弈论方法 |
课程来源: | 视频讲座网 |
最后编审: | 2020-10-22:chenxin |
阅读次数: | 83 |