arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1906.01404cs.LGstat.ML
收藏

高斯过程的后验方差分析及其在平均学习曲线中的应用

Posterior Variance Analysis of Gaussian Processes with Application to Average Learning Curves

Technical University of Munich(慕尼黑工业大学)

Armin Lederer, Jonas Umlauft, Sandra Hirche

摘要:

高斯过程的后验方差是学习误差的一个有价值的度量,它在安全强化学习和控制设计等各种应用中得到了利用。然而,缺乏对后验方差的适当分析,该分析捕获了有限和无限数量的训练数据的行为。本文推导了一种新的后验方差函数的界,它只需要局部信息,因为它只依赖于在所考虑的测试点附近的训练样本的数量。此外,我们证明了充分条件,确保后验方差收敛到零。最后,我们证明了我们的平均学习界的扩展优于现有的方法。

英文摘要:

The posterior variance of Gaussian processes is a valuable measure of the learning error which is exploited in various applications such as safe reinforcement learning and control design. However, suitable analysis of the posterior variance which captures its behavior for finite and infinite number of training data is missing. This paper derives a novel bound for the posterior variance function which requires only local information because it depends only on the number of training samples in the proximity of a considered test point. Furthermore, we prove sufficient conditions which ensure the convergence of the posterior variance to zero. Finally, we demonstrate that the extension of our bound to an average learning bound outperforms existing approaches.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑