arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2110.05997math.NAcs.NA
收藏

张量分解和算法及其在张量学习中的应用

Tensor decompositions and algorithms, with applications to tensor learning

Felipe Bottega Diniz

摘要:

提出了一种新的典型多进分解算法。它的特点是比现有技术实现方式更低的计算复杂性和存储器使用。我们从CPD应用于现实世界问题的一些例子开始。以下是对这项工作的主要贡献的简短总结。在第一章中,我们回顾了经典的张量代数和几何,重点是CPD。第二章侧重于张量压缩,这被认为是(在这项工作中)CPD算法的最重要的部分之一。在第三章中,我们讨论了高斯-牛顿法,这是一种用于最小化非线性函数的非线性最小二乘法。第四章是全文最长的一章。在这一章中,我们介绍了本文的主要研究对象:张量Fox。基本上,它是一个张量包,其中包括CPD求解器。在介绍了Tensor Fox之后,我们将进行大量的计算实验,将这个求解器与其他几个求解器进行比较。在本章的最后,我们将介绍张量训练分解,并展示如何使用它来计算高阶CPD。我们还讨论了一些重要的细节,如正则化,预处理,条件,并行等,在第5章中,我们考虑张量分解和机器学习之间的交叉。介绍了一种新的模型,它作为一个张量版本的神经网络。最后,在第六章中,我们得出了最后的结论,并介绍了我们对未来发展的展望。

英文摘要:

A new algorithm of the canonical polyadic decomposition (CPD) presented here. It features lower computational complexity and memory usage than the available state of the art implementations. We begin with some examples of CPD applications to real world problems. A short summary of the main contributions in this work follows. In chapter 1 we review classical tensor algebra and geometry, with focus on the CPD. Chapter 2 focuses on tensor compression, which is considered (in this work) to be one of the most important parts of the CPD algorithm. In chapter 3 we talk about the Gauss-Newton method, which is a nonlinear least squares method used to minimize nonlinear functions. Chapter 4 is the longest one of this thesis. In this chapter we introduce the main character of this thesis: Tensor Fox. Basically it is a tensor package which includes a CPD solver. After introducing Tensor Fox we will conduct lots of computational experiments comparing this solver with several others. At the end of this chapter we introduce the Tensor Train decomposition and show how to use it to compute higher order CPDs. We also discuss some important details such as regularization, preconditioning, conditioning, parallelism, etc. In chapter 5 we consider the intersection between tensor decompositions and machine learning. A novel model is introduced, which works as a tensor version of neural networks. Finally, in chapter 6 we reach the final conclusions and introduce our expectations for future developments.

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。

↑