Poster
in
Workshop: Causal Representation Learning
Invariance & Causal Representation Learning: Prospects and Limitations
Simon Bing · Jonas Wahl · Urmi Ninad · Jakob Runge
Keywords: [ Invariance ] [ causal representation learning ] [ distributional robustness ] [ out-of-distribution prediciton ] [ identifiability ] [ invariant prediction ]
In causal models, a given mechanism is assumed to be invariant to changes of other mechanisms. While this principle has been utilized for inference in settings where the causal variables are observed, theoretical insights when the variables of interest are latent are largely missing. We assay the connection between invariance and causal representation learning by establishing impossibility results which show that invariance alone is insufficient to identify latent causal variables. Together with practical considerations, we use these theoretical findings to highlight the need for additional constraints in order to identify representations by exploiting invariance.