arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1809.05043stat.MLcs.LG
收藏

PhD博士论文:有限字母表上的广义独立分量分析

PhD Dissertation: Generalized Independent Components Analysis Over Finite Alphabets

Tel-Aviv University(特拉维夫大学);The Raymond and Beverly Sackler Faculty of Exact Sciences(雷蒙德与贝弗利·萨克勒精确科学学院)

Amichai Painsky

摘要:

独立成分分析(ICA)是一种统计方法,用于将可观察的多维随机向量转换为尽可能相互统计独立的成分。通常ICA框架假设一个模型,根据该模型生成观测值(例如具有加性噪声的线性变换)。有限域上的ICA是ICA的一种特殊情况,其中观测值和独立分量都在有限字母表上。在这篇论文中,我们考虑了有限场的情况下,一个观察向量被分解为它的独立分量(尽可能多),没有事先假设的方式,它的产生。这种推广也被称为巴洛的最小冗余表示,并被认为是一个开放的问题。我们提出了几个定理,并表明,这个困难的问题可以准确地解决了分支定界搜索树算法,或紧密近似的一系列线性问题。此外,我们还证明了存在一个简单的变换(即顺序排列),它提供了一个贪婪但非常有效的近似最优解。我们进一步表明,虽然不是每个随机向量都可以有效地分解成独立的分量,但随着维数的增加,绝大多数向量确实分解得很好(即在一个小的恒定成本内)。此外,我们表明,我们实际上可以实现这个有利的恒定成本的复杂性是渐近线性的字母表大小。我们的贡献提供了第一个有效的解决方案,巴洛的问题与理论和计算的保证。最后,我们展示了我们建议的框架在多源编码应用程序。

英文摘要:

Independent component analysis (ICA) is a statistical method for transforming an observable multi-dimensional random vector into components that are as statistically independent as possible from each other. Usually the ICA framework assumes a model according to which the observations are generated (such as a linear transformation with additive noise). ICA over finite fields is a special case of ICA in which both the observations and the independent components are over a finite alphabet. In this thesis we consider a formulation of the finite-field case in which an observation vector is decomposed to its independent components (as much as possible) with no prior assumption on the way it was generated. This generalization is also known as Barlow's minimal redundancy representation and is considered an open problem. We propose several theorems and show that this hard problem can be accurately solved with a branch and bound search tree algorithm, or tightly approximated with a series of linear problems. Moreover, we show that there exists a simple transformation (namely, order permutation) which provides a greedy yet very effective approximation of the optimal solution. We further show that while not every random vector can be efficiently decomposed into independent components, the vast majority of vectors do decompose very well (that is, within a small constant cost), as the dimension increases. In addition, we show that we may practically achieve this favorable constant cost with a complexity that is asymptotically linear in the alphabet size. Our contribution provides the first efficient set of solutions to Barlow's problem with theoretical and computational guarantees. Finally, we demonstrate our suggested framework in multiple source coding applications.

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。

↑