`

Timezone: »

 
Poster
Independent mechanism analysis, a new concept?
Luigi Gresele · Julius von Kügelgen · Vincent Stimper · Bernhard Schölkopf · Michel Besserve

Thu Dec 09 12:30 AM -- 02:00 AM (PST) @
in Poster Session 5 »

Independent component analysis provides a principled framework for unsupervised representation learning, with solid theory on the identifiability of the latent code that generated the data, given only observations of mixtures thereof. Unfortunately, when the mixing is nonlinear, the model is provably nonidentifiable, since statistical independence alone does not sufficiently constrain the problem. Identifiability can be recovered in settings where additional, typically observed variables are included in the generative process. We investigate an alternative path and consider instead including assumptions reflecting the principle of independent causal mechanisms exploited in the field of causality. Specifically, our approach is motivated by thinking of each source as independently influencing the mixing process. This gives rise to a framework which we term independent mechanism analysis. We provide theoretical and empirical evidence that our approach circumvents a number of nonidentifiability issues arising in nonlinear blind source separation.

Keywords: Theory · Representation Learning · Causality

Author Information

Luigi Gresele (MPI for Intelligent Systems, Tübingen)
Julius von Kügelgen (Max Planck Institute for Intelligent Systems Tübingen & University of Cambridge)
Vincent Stimper (University of Cambridge)
Bernhard Schölkopf (MPI for Intelligent Systems, Tübingen)
Michel Besserve (MPI for Intelligent Systems, Tübingen)

More from the Same Authors