DeepAI AI Chat
Log In Sign Up

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

07/21/2021
by   Sébastien Lachapelle, et al.
23

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

06/09/2021

Independent mechanism analysis, a new concept?

Independent component analysis provides a principled framework for unsup...
01/14/2020

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

A central question of representation learning asks under which condition...
07/15/2022

Partial Disentanglement via Mechanism Sparsity

Disentanglement via mechanism sparsity was introduced recently as a prin...
07/13/2022

Probing the Robustness of Independent Mechanism Analysis for Representation Learning

One aim of representation learning is to recover the original latent cod...
05/16/2016

Geometry Aware Mappings for High Dimensional Sparse Factors

While matrix factorisation models are ubiquitous in large scale recommen...
06/02/2022

Weakly Supervised Representation Learning with Sparse Perturbations

The theory of representation learning aims to build methods that provabl...
02/02/2023

Disentanglement of Latent Representations via Sparse Causal Interventions

The process of generating data such as images is controlled by independe...