The Information Sieve
It addresses the problem of extracting interpretable latent structures from data for researchers in machine learning, though it appears incremental as it builds on existing unsupervised methods.
The paper tackles unsupervised representation learning by introducing a hierarchical decomposition framework that recovers latent factors explaining multivariate dependence, applying it to tasks like independent component analysis, compression, and missing value prediction.
We introduce a new framework for unsupervised learning of representations based on a novel hierarchical decomposition of information. Intuitively, data is passed through a series of progressively fine-grained sieves. Each layer of the sieve recovers a single latent factor that is maximally informative about multivariate dependence in the data. The data is transformed after each pass so that the remaining unexplained information trickles down to the next layer. Ultimately, we are left with a set of latent factors explaining all the dependence in the original data and remainder information consisting of independent noise. We present a practical implementation of this framework for discrete variables and apply it to a variety of fundamental tasks in unsupervised learning including independent component analysis, lossy and lossless compression, and predicting missing values in data.