From the 3 of 10 linked papers with an AI index.
10 papers
Relaxing Faithfulness with Intervention-Only Causal Discovery
Bijan Mazaheri, Jiaqi Zhang, Caroline Uhler
The paper proposes using hard interventions as the primary source of information for learning causal graphs, introducing a relaxed faithfulness assumption that tolerates pathway ca…
Meta-Dependence in Conditional Independence Testing
Bijan Mazaheri, Jiaqi Zhang, Caroline Uhler
The paper proposes a simple-to-compute measure of meta‑dependence among conditional independence statements using moment projections, provides a closed‑form solution for multivaria…
Causal Discovery in Mixtures of Populations
Bijan Mazaheri, Spencer Gordon, Yuval Rabani +1
The paper proposes a method to identify causal graphs in data that come from a mixture of a few latent populations, even when a global latent confounder is present, by using rank p…
The Spectral Structure of Latent Treatment Effects
Hamza Virk, Bijan Mazaheri, Yihren Wu
Identifying heterogeneous treatment effects under unobserved confounding is central in observational causal inference. In proxy models with a discrete latent confounder, prior Synt…
Masking Causality and Conditional Dependence
Zou Yang, Sophia Xiao, Bijan Mazaheri
Many regulatory and analytic problems require that a prohibited variable influence a decision only through a designated allowable channel -- a conditional-independence requirement…
Causal Foundations of Collective Agency
Frederik Hytting Jørgensen, Sebastian Weichwald, Lewis Hammond
A key challenge for the safety of advanced AI systems is the possibility that multiple simpler agents might inadvertently form a collective agent with capabilities and goals distin…