Linear Causal Disentanglement via Interventions
Jul 24, 2023
Speakers
Chandler Squires
Speaker · 0 followers
Anna Seigal
Speaker · 0 followers
Salil Bhate
Speaker · 0 followers
Caroline Uhler
Speaker · 2 followers
About
Causal disentanglement seeks a representation of data involving latent variables that are related via a causal model. A representation is identifiable if both the latent model and the transformation from latent to observed variables are unique. In this paper, we study observed variables that are a linear transformation of a linear latent causal model. Data from interventions are necessary for identifiability: if one latent variable is missing an intervention, we show that there exist distinct models that cannot be distinguished. Conversely, we show that a single intervention on each latent variable is sufficient for identifiability. Our proof uses a generalization of the RQ decomposition of a matrix that replaces the usual orthogonal and upper triangular conditions with analogues depending on a partial order on the rows of the matrix, with partial order determined by a latent causal model. We corroborate our theoretical results with a method for causal disentanglement. We show that the method accurately recovers a latent causal model on synthetic and semi-synthetic data and we illustrate a use case on a dataset of single-cell RNA sequencing measurements.Causal disentanglement seeks a representation of data involving latent variables that are related via a causal model. A representation is identifiable if both the latent model and the transformation from latent to observed variables are unique. In this paper, we study observed variables that are a linear transformation of a linear latent causal model. Data from interventions are necessary for identifiability: if one latent variable is missing an intervention, we show that there exist distinct mo…
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
The Benefits of Model-Based Generalization in Reinforcement Learning
Watch later
Kenny Young, …
On the Connection Between MPNN and Graph Transformer
Watch later
Chen Cai, …
Evolving Semantic Prototype Improves Generative Zero-Shot Learning
Watch later
Shiming Chen, …
FedHPO-Bench: A Benchmark Suite for Federated Hyperparameter Optimization
Watch later
Zhen Wang, …
Bootstrapped Representations in Reinforcement Learning
Watch later
Do Not Train It: A Linear Neural Architecture Search of Graph Neural Networks
Watch later
Peng Xu, …