TL;DR本文介绍了使用核方法进行多视图潜变量模型学习的理论。方法利用复现核希尔伯特空间嵌入多视图潜变量的联合分布,并提出了一种有效的张量幂法来恢复潜变量参数。实验结果展示了该非参数模型在多个方面都优于现有光谱算法和 EM 算法。
Abstract
spectral methods have greatly advanced the estimation of latent variable
models, generating a sequence of novel and efficient algorithms with strong
theoretical guarantees. However, current spectral algorithms are largely
restricted to mixtures of discrete or Gaussian distributions. In