Guy Katz

Formal Mechanistic Interpretability: Automated Circuit Discovery with Provable Guarantees

Unifying Formal Explanations: A Complexity-Theoretic Perspective

Provably Explaining Neural Additive Models

FAME: Formal Abstract Minimal Explanation for Neural Networks

Bridging Efficiency and Safety: Formal Verification of Neural Networks with Early Exits

Lookahead Branching for Neural Network Verification

SHAP Meets Tensor Networks: Provably Tractable Explanations with Parallelism

Additive Models Explained: A Computational Complexity Approach

Abstracting and Refining Provably Sufficient Explanations of Neural Network Predictions

Explaining, Fast and Slow: Abstraction and Refinement of Provable Explanations

On the (un) interpretability of Ensembles: A Computational Analysis

What makes an Ensemble (Un) Interpretable?