Matches in SemOpenAlex for { <https://semopenalex.org/work/W4381573485> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W4381573485 abstract "Learning latent causal models from data has many important applications such as robustness, model extrapolation, and counterfactuals. Most prior theoretic work has focused on full causal discovery (i.e., recovering the true latent variables) but requires strong assumptions such as linearity or fails to have any analysis of the equivalence class of solutions (e.g., IRM). Instead of full causal discovery, we focus on a specific type of causal query called the domain counterfactual, which hypothesizes what a sample would have looked like if it had been generated in a different domain (or environment). Concretely, we assume domain-specific invertible latent structural causal models and a shared invertible observation function, both of which are less restrictive assumptions than prior theoretic works. Under these assumptions, we define domain counterfactually equivalent models and prove that any model can be transformed into an equivalent model via two invertible functions. This constructive property provides a tight characterization of the domain counterfactual equivalence classes. Building upon this result, we prove that every equivalence class contains a model where all intervened variables are at the end when topologically sorted by the causal DAG, i.e., all non-intervened variables have non-intervened ancestors. This surprising result suggests that an algorithm that only allows intervention in the last $k$ latent variables may improve model estimation for counterfactuals. In experiments, we enforce the sparse intervention hypothesis via this theoretic result by constraining that the latent SCMs can only differ in the last few causal mechanisms and demonstrate the feasibility of this algorithm in simulated and image-based experiments." @default.
- W4381573485 created "2023-06-22" @default.
- W4381573485 creator A5000799899 @default.
- W4381573485 creator A5015210439 @default.
- W4381573485 creator A5055431348 @default.
- W4381573485 creator A5067212035 @default.
- W4381573485 creator A5074209565 @default.
- W4381573485 date "2023-06-20" @default.
- W4381573485 modified "2023-10-17" @default.
- W4381573485 title "Towards Characterizing Domain Counterfactuals For Invertible Latent Causal Models" @default.
- W4381573485 doi "https://doi.org/10.48550/arxiv.2306.11281" @default.
- W4381573485 hasPublicationYear "2023" @default.
- W4381573485 type Work @default.
- W4381573485 citedByCount "0" @default.
- W4381573485 crossrefType "posted-content" @default.
- W4381573485 hasAuthorship W4381573485A5000799899 @default.
- W4381573485 hasAuthorship W4381573485A5015210439 @default.
- W4381573485 hasAuthorship W4381573485A5055431348 @default.
- W4381573485 hasAuthorship W4381573485A5067212035 @default.
- W4381573485 hasAuthorship W4381573485A5074209565 @default.
- W4381573485 hasBestOaLocation W43815734851 @default.
- W4381573485 hasConcept C105795698 @default.
- W4381573485 hasConcept C108650721 @default.
- W4381573485 hasConcept C11671645 @default.
- W4381573485 hasConcept C118615104 @default.
- W4381573485 hasConcept C149782125 @default.
- W4381573485 hasConcept C15744967 @default.
- W4381573485 hasConcept C202444582 @default.
- W4381573485 hasConcept C2777044963 @default.
- W4381573485 hasConcept C2780069185 @default.
- W4381573485 hasConcept C33923547 @default.
- W4381573485 hasConcept C41008148 @default.
- W4381573485 hasConcept C51167844 @default.
- W4381573485 hasConcept C70727504 @default.
- W4381573485 hasConcept C71889745 @default.
- W4381573485 hasConcept C77805123 @default.
- W4381573485 hasConcept C96442724 @default.
- W4381573485 hasConceptScore W4381573485C105795698 @default.
- W4381573485 hasConceptScore W4381573485C108650721 @default.
- W4381573485 hasConceptScore W4381573485C11671645 @default.
- W4381573485 hasConceptScore W4381573485C118615104 @default.
- W4381573485 hasConceptScore W4381573485C149782125 @default.
- W4381573485 hasConceptScore W4381573485C15744967 @default.
- W4381573485 hasConceptScore W4381573485C202444582 @default.
- W4381573485 hasConceptScore W4381573485C2777044963 @default.
- W4381573485 hasConceptScore W4381573485C2780069185 @default.
- W4381573485 hasConceptScore W4381573485C33923547 @default.
- W4381573485 hasConceptScore W4381573485C41008148 @default.
- W4381573485 hasConceptScore W4381573485C51167844 @default.
- W4381573485 hasConceptScore W4381573485C70727504 @default.
- W4381573485 hasConceptScore W4381573485C71889745 @default.
- W4381573485 hasConceptScore W4381573485C77805123 @default.
- W4381573485 hasConceptScore W4381573485C96442724 @default.
- W4381573485 hasLocation W43815734851 @default.
- W4381573485 hasOpenAccess W4381573485 @default.
- W4381573485 hasPrimaryLocation W43815734851 @default.
- W4381573485 hasRelatedWork W1485303311 @default.
- W4381573485 hasRelatedWork W1494043421 @default.
- W4381573485 hasRelatedWork W1584341211 @default.
- W4381573485 hasRelatedWork W2530023256 @default.
- W4381573485 hasRelatedWork W2885531937 @default.
- W4381573485 hasRelatedWork W3214040448 @default.
- W4381573485 hasRelatedWork W4221146053 @default.
- W4381573485 hasRelatedWork W4287375102 @default.
- W4381573485 hasRelatedWork W4287605938 @default.
- W4381573485 hasRelatedWork W4296931829 @default.
- W4381573485 isParatext "false" @default.
- W4381573485 isRetracted "false" @default.
- W4381573485 workType "article" @default.