线性ICA的双射特征映射学习
Learning Bijective Feature Maps for Linear ICA
摘要:
将图像等高维数据分解为独立的潜在因子,即独立分量分析(ICA),一直是一个开放的研究课题。正如我们所展示的,现有的概率深度生成模型(DGMs)是为图像数据量身定制的,在非线性ICA任务上表现不佳。为了解决这个问题,我们提出了一种DGM,它将双射特征映射与线性ICA模型相结合,以学习高维数据的可解释潜在结构。鉴于联合训练这样一个混合模型的复杂性,我们引入了新的理论,约束线性ICA躺在靠近正交矩形矩阵的流形,Stiefel流形。通过这样做,我们创建的模型收敛速度快,易于训练,并实现更好的无监督潜在因素发现比基于流的模型,线性ICA,和图像上的变分自编码器。
英文摘要:
Separating high-dimensional data like images into independent latent factors, i.e independent component analysis (ICA), remains an open research problem. As we show, existing probabilistic deep generative models (DGMs), which are tailor-made for image data, underperform on non-linear ICA tasks. To address this, we propose a DGM which combines bijective feature maps with a linear ICA model to learn interpretable latent structures for high-dimensional data. Given the complexities of jointly training such a hybrid model, we introduce novel theory that constrains linear ICA to lie close to the manifold of orthogonal rectangular matrices, the Stiefel manifold. By doing so we create models that converge quickly, are easy to train, and achieve better unsupervised latent factor discovery than flow-based models, linear ICA, and Variational Autoencoders on images.
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。