arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.01432stat.MLcs.LG
收藏

非线性函数输出回归:一种字典方法

Nonlinear Functional Output Regression: a Dictionary Approach

LTCI, Télécom Paris, Institut Polytechnique de Paris(巴黎理工学院巴黎电信学院LTCI实验室);Université de Lorraine, CNRS, IECL(洛林大学法国国家科学研究中心IECL实验室)

Dimitri Bouche, Marianne Clausel, François Roueff, Florence d'Alché-Buc

摘要:

为了解决函数输出回归,我们引入了投影学习(PL),这是一种基于字典的新方法,它学习预测在字典上扩展的函数,同时最小化基于功能损失的经验风险。PL使得使用非正交字典成为可能,然后可以与字典学习相结合;因此,它比依赖于向量损失的基于扩展的方法灵活得多。这种一般方法的实例与再生核希尔伯特空间的向量值函数作为基于核的投影学习(KPL)。对于函数平方损失,提出了两个封闭形式的估计,一个是完全观测的输出函数,另一个是部分观测的。这两种理论都有超额风险分析的支持。然后,在更一般的设置的积分损失的基础上可微的接地损耗,KPL实施使用一阶优化的完全和部分观察的输出函数。最后,所提出的算法的几个鲁棒性方面突出了玩具数据集和两个真实的数据集上的研究表明,它们是有竞争力的相比,其他非线性方法。值得注意的是,使用平方损失和学习字典,KPL在计算成本和性能之间享有特别有吸引力的权衡。

英文摘要:

To address functional-output regression, we introduce projection learning (PL), a novel dictionary-based approach that learns to predict a function that is expanded on a dictionary while minimizing an empirical risk based on a functional loss. PL makes it possible to use non orthogonal dictionaries and can then be combined with dictionary learning; it is thus much more flexible than expansion-based approaches relying on vectorial losses. This general method is instantiated with reproducing kernel Hilbert spaces of vector-valued functions as kernel-based projection learning (KPL). For the functional square loss, two closed-form estimators are proposed, one for fully observed output functions and the other for partially observed ones. Both are backed theoretically by an excess risk analysis. Then, in the more general setting of integral losses based on differentiable ground losses, KPL is implemented using first-order optimization for both fully and partially observed output functions. Eventually, several robustness aspects of the proposed algorithms are highlighted on a toy dataset; and a study on two real datasets shows that they are competitive compared to other nonlinear approaches. Notably, using the square loss and a learnt dictionary, KPL enjoys a particularily attractive trade-off between computational cost and performances.

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。

↑