Timezone: »

Discovering Latent Causal Variables via Mechanism Sparsity: A New Principle for Nonlinear ICA
Sebastien Lachapelle · Pau Rodriguez · Remi Le Priol · Alexandre Lacoste

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.

Author Information

Sebastien Lachapelle (Mila, Université de Montréal)
Pau Rodriguez (Element AI)
Remi Le Priol (Mila, Université de Montréal)
Alexandre Lacoste (ServiceNow)

More from the Same Authors