arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.01545cs.LGstat.ML
收藏

基于Fourier特征和张量分解的大规模学习

Large-Scale Learning with Fourier Features and Tensor Decompositions

Delft University of Technology(代尔夫特理工大学)

Frederiek Wesel, Kim Batselier

摘要:

随机傅立叶特征提供了一种用核方法解决大规模机器学习问题的方法。他们缓慢的蒙特卡罗收敛速度激发了确定性傅立叶特征的研究,其近似误差可以在基函数的数量上呈指数下降。然而,由于它们的张量积扩展到多个维度,这些方法严重地遭受维度灾难,限制了它们对一维,二维或三维场景的适用性。在我们的方法中,我们通过利用确定性傅立叶特征的张量积结构来克服所述维数灾难,这使我们能够将模型参数表示为低秩张量分解。我们推导出一个单调收敛的块坐标下降算法,在正则化平方损失函数的输入的样本大小和维度上都具有线性复杂度,允许学习使用确定性傅立叶特征的分解形式的简约模型。我们通过数值实验证明了我们的低秩张量方法如何获得与相应的非参数模型相同的性能,始终优于随机傅立叶特征。

英文摘要:

Random Fourier features provide a way to tackle large-scale machine learning problems with kernel methods. Their slow Monte Carlo convergence rate has motivated the research of deterministic Fourier features whose approximation error can decrease exponentially in the number of basis functions. However, due to their tensor product extension to multiple dimensions, these methods suffer heavily from the curse of dimensionality, limiting their applicability to one, two or three-dimensional scenarios. In our approach we overcome said curse of dimensionality by exploiting the tensor product structure of deterministic Fourier features, which enables us to represent the model parameters as a low-rank tensor decomposition. We derive a monotonically converging block coordinate descent algorithm with linear complexity in both the sample size and the dimensionality of the inputs for a regularized squared loss function, allowing to learn a parsimonious model in decomposed form using deterministic Fourier features. We demonstrate by means of numerical experiments how our low-rank tensor approach obtains the same performance of the corresponding nonparametric model, consistently outperforming random Fourier features.

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。

↑