论文标题
线性ICA的学习射击性特征图
Learning Bijective Feature Maps for Linear ICA
论文作者
论文摘要
将图像（例如独立组件分析（ICA））等高维数据（例如图像）分开，仍然是一个开放的研究问题。如我们所示，现有的概率深层生成模型（DGM）是针对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，我们提出了一个DGM，该DGM结合了双线性ICA模型，以学习用于高维数据的可解释潜在结构。鉴于共同训练这种混合模型的复杂性，我们引入了新的理论，该理论将线性ICA限制为靠近正交矩形矩阵（Stiefel歧管）的歧管。通过这样做，我们创建的模型可以快速收敛，易于训练，并且比基于流的模型，线性ICA和图像上的变异自动编码器获得更好的无监督潜在因素发现。
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.
