Temporal data, representing chronological observations of complex systems, has always
been a typical data structure that can be widely generated by many domains, such as …

Causal representation learning seeks to extract high-level latent factors from low-level
sensory data. Most existing methods rely on observational data and structural assumptions …

Learning high-level causal representations together with a causal model from unstructured
low-level data such as pixels is impossible from observational data alone. We prove under …

Causal disentanglement aims to uncover a representation of data using latent variables that
are interrelated through a causal model. Such a representation is identifiable if the latent …

We study causal representation learning, the task of inferring latent causal variables and
their causal relations from high-dimensional functions (“mixtures”) of the variables. Prior …

We study the problem of learning causal representations from unknown, latent interventions
in a general setting, where the latent distribution is Gaussian but the mixing function is …

Abstract Independent Component Analysis (ICA) aims to recover independent latent
variables from observed mixtures thereof. Causal Representation Learning (CRL) aims …

Temporal data representing chronological observations of complex systems can be
ubiquitously collected in smart industry, medicine, finance and etc. In the last decade, many …

The theory of representation learning aims to build methods that provably invert the data
generating process with minimal domain knowledge or any source of supervision. Most prior …

Recently in the field of unsupervised representation learning, strong identifiability results for
disentanglement of causally-related latent variables have been established by exploiting …