arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1402.5876stat.MLcs.LG
收藏

回归的流形高斯过程

Manifold Gaussian Processes for Regression

Technische Universität Darmstadt(达姆施塔特工业大学);Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所);University of Cambridge(剑桥大学);Imperial College London(帝国理工学院)

Roberto Calandra, Jan Peters, Carl Edward Rasmussen, Marc Peter Deisenroth

摘要:

现成的高斯过程(GP)协方差函数对要建模的函数的结构上的平滑性假设进行编码。为了对复杂和不可微的函数建模,这些平滑性假设通常限制太多。缓解这种限制的一种方法是通过引入特征空间来找到数据的不同表示。这个特征空间通常是以无监督的方式学习的,这可能会导致数据表示对整个回归任务没有用处。在本文中,我们提出了流形高斯过程,这是一种新的监督方法,它联合学习数据到特征空间的变换和从特征空间到观察空间的GP回归。Manifold GP是一个完整的GP,允许学习数据表示,这对整个回归任务很有用。作为一个概念验证,我们评估了我们的方法在复杂的非光滑功能,标准的GP表现不佳,如步骤功能和机器人任务的接触。

英文摘要:

Off-the-shelf Gaussian Process (GP) covariance functions encode smoothness assumptions on the structure of the function to be modeled. To model complex and non-differentiable functions, these smoothness assumptions are often too restrictive. One way to alleviate this limitation is to find a different representation of the data by introducing a feature space. This feature space is often learned in an unsupervised way, which might lead to data representations that are not useful for the overall regression task. In this paper, we propose Manifold Gaussian Processes, a novel supervised method that jointly learns a transformation of the data into a feature space and a GP regression from the feature space to observed space. The Manifold GP is a full GP and allows to learn data representations, which are useful for the overall regression task. As a proof-of-concept, we evaluate our approach on complex non-smooth functions where standard GPs perform poorly, such as step functions and robotics tasks with contacts.

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。

↑