← Search

Ehsan Sharifian

2 accepted papers

2025

A New Approach to Backtracking Counterfactual Explanations: A Unified Causal Framework for Efficient Model Interpretability

ICML 2025poster

Counterfactual explanations enhance interpretability by identifying alternative inputs that produce different outputs, offering localized insights into model decisions. However, traditional methods often neglect causal relationships, leading to unrealistic examples. While newer approaches integrate…

Cited by 0SourcePDFScholar
2025

Near-Optimal Experiment Design in Linear non-Gaussian Cyclic Models

NeurIPS 2025spotlight

We study the problem of causal structure learning from a combination of observational and interventional data generated by a linear non-Gaussian structural equation model that might contain cycles. Recent results show that using mere observational data identifies the causal graph only up to a permut…

Cited by 0SourceScholar