AI Paper Atlas

Research map / Probabilistic and scientific modeling / Causal discovery

Causal Imitability Under Context-Specific Independence Relations

Fateme Jamshidi, Sina Akbari, Negar Kiyavash

NeurIPS 2023 · Probabilistic and scientific modeling › Causal discovery · approach: Causal representation identifiability · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Account for CSI relations when deciding imitabilityrandom graphs with n vertices · Random graphs, 3 context variablesfraction of imitable instancesImproved
Use CSI-based Algorithm 1 instead of Naive 1 (mimic P(X))Algorithm 1 · Synthetic modelE[Y]: 1.194 -> 1.358Improved
Use CSI-based Algorithm 1 instead of Naive 2 (behavior cloning on ancestors)Algorithm 1 · Synthetic modelE[Y]: 1.193 -> 1.358Improved
Use Algorithm 1 instead of Naive 1Algorithm 1 · Synthetic modelKL of reward distribution to expert: 0.0217 -> 0.0007Improved
Use Algorithm 1 instead of Naive 2Algorithm 1 · Synthetic modelKL of reward distribution to expert: 0.0219 -> 0.0007Improved
Use Algorithm 1 instead of Naive 1Algorithm 1 · Synthetic modelpolicy estimation KL, T=0: 2.3 \times 10^{-5} -> 1.3\times 10^{-3}Hurt
Use Algorithm 1 instead of Naive 2Algorithm 1 · Synthetic modelpolicy estimation KL, T=1: 4.8 \times 10^{-4} -> 1.3\times 10^{-3}Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy