Discovering Latent Causal Variables via Mechanism Sparsity: A New Principle for Nonlinear ICA

by   Sébastien Lachapelle, et al.

It can be argued that finding an interpretable low-dimensional representation of a potentially high-dimensional phenomenon is central to the scientific enterprise. Independent component analysis (ICA) refers to an ensemble of methods which formalize this goal and provide estimation procedure for practical application. This work proposes mechanism sparsity regularization as a new principle to achieve nonlinear ICA when latent factors depend sparsely on observed auxiliary variables and/or past latent factors. We show that the latent variables can be recovered up to a permutation if one regularizes the latent mechanisms to be sparse and if some graphical criterion is satisfied by the data generating process. As a special case, our framework shows how one can leverage unknown-target interventions on the latent factors to disentangle them, thus drawing further connections between ICA and causality. We validate our theoretical results with toy experiments.



There are no comments yet.


page 1

page 2

page 3

page 4


Independent mechanism analysis, a new concept?

Independent component analysis provides a principled framework for unsup...

Disentanglement by Nonlinear ICA with General Incompressible-flow Networks (GIN)

A central question of representation learning asks under which condition...

Learning latent causal graphs via mixture oracles

We study the problem of reconstructing a causal graphical model from dat...

Geometry Aware Mappings for High Dimensional Sparse Factors

While matrix factorisation models are ubiquitous in large scale recommen...

A Unified Probabilistic Model for Learning Latent Factors and Their Connectivities from High-Dimensional Data

Connectivity estimation is challenging in the context of high-dimensiona...

Nonlinear ICA Using Auxiliary Variables and Generalized Contrastive Learning

Nonlinear ICA is a fundamental problem for unsupervised representation l...

Neural Ideal Point Estimation Network

Understanding politics is challenging because the politics take the infl...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.