Connections with Robust PCA and the Role of Emergent Sparsity in Variational Autoencoder Models

84 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Diagnosing and Enhancing VAE Models (2019, background): “As discussed in (Dai et al., 2018)[Section 4], if the decoder mean network becomes inordinately complex/deep, then a useless degenerate solution involving the implicit memorization of training data can break even the natural VAE regularization mechanisms we have described herein (in principle, this…”
Guided Variational Autoencoder for Disentanglement Learning (2020, background): “Connections between robust PCA [7] and VAE [29] have been observed [10].”
Hidden Talents of the Variational Autoencoder. (2017, background): “t robust PCA models, capable of learning nonlinear manifolds of unknown dimension obscured by gross corruptions. A version of this work has appeared in the Journal of Machine Learning Research (JMLR) [13]; however, we include several small updates here. Keywords: Variational Autoencoder, Deep Genera”
MIWAE: Deep Generative Modelling and Imputation of Incomplete Data Sets (2019, methodology): “They can be seen as nonlinear extensions of factor analysis and have links with robust principal component analysis (Dai et al., 2018) and nonparametric mixture models (Mattei & Frellsen, 2018a).”