Research map / Probabilistic and scientific modeling / Causal discovery
Transporting the Past: An Optimal Transport View of Backtracking Counterfactuals
Zhangyi Liu, Sayedpouria Fatemi, Suvrit Sra
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Frames backtracking counterfactual inference in SCMs as optimal transport, transporting the posterior over exogenous variables onto the set of exogenous configurations that yield a desired counterfactual outcome.
Problem
Backtracking counterfactual inference in structural causal models: a factual observation induces a posterior over exogenous variables, so counterfactual inference is distributional rather than point-valued.
Approach
Two complementary optimal-transport frameworks move the exogenous posterior onto the set of exogenous configurations satisfying the desired counterfactual condition, giving a distributional treatment of backtracking counterfactuals.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| allow dependence among counterfactual exogenous variables (OT-CF) instead of enforcing independence (ablation) | OT-CF · 5D nonlinear | D_U: 0.240670 vs 0.250959 (Hard) | Mixed |
| use Hard constrained solver instead of soft solvers | IOT-CF · synthetic SCMs | CF residual: exact CF satisfaction | Improved |
| use Hard constrained solver instead of OT-CF | IOT-CF · 10D nonlinear | D_U: 0.795014 (OT-CF) vs 0.798030 (Hard) | No clear effect |
| use Penalty instead of Marginal solver (ablation) | IOT-CF · 6D polynomial | D_U: 0.783031 -> 0.384916 | Improved |
| use OT-CF instead of interventional counterfactual | OT-CF · 5D nonlinear | D_U: 0.4216 -> 0.2407 | Improved |
| increase Gaussian transfer kernel parameter from 0.5 to 50 (ablation) | probabilistic backtracking · Example 1 | D_K: 2.566089 -> 0.151979 | Improved |
| increase Gaussian transfer kernel parameter from 0.5 to 50 (ablation) | probabilistic backtracking · Example 2 | D_K: 2.212211 -> 0.070130 | Improved |
| add independence constraint (IOT-CF) to OT-CF (ablation) | IOT-CF · illustrative Example | counterfactual outcome uniqueness | Improved |
Closest papers by meaning
- A New Approach to Backtracking Counterfactual Explanations: A Unified Causal Framework for Efficient Model Interpretability (ICML 2025 · similarity 0.89)
- Towards Characterizing Domain Counterfactuals for Invertible Latent Causal Models (ICLR 2024 · similarity 0.88)
- Cyclic Counterfactuals under Shift–Scale Interventions (NeurIPS 2025 · similarity 0.87)
- Model Reconstruction Using Counterfactual Explanations: A Perspective From Polytope Theory (NeurIPS 2024 · similarity 0.87)
- Reducing Balancing Error for Causal Inference via Optimal Transport (ICML 2024 · similarity 0.87)
- Causal learning with the invariance principle (NeurIPS 2026 · similarity 0.87)
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.
