Practical and Efficient Rashomon Set Sampling for Model Interpretability

Explaining a single model can be misleading when many near-optimal models (a Rashomon set) yield different feature attributions. We frame this as a Rashomon set sampling problem and propose two practical axioms that any Rashomon sampler should satisfy: generalizability (meaning it must accept arbitrary reference models and loss functions) and Implementation Sparsity (meaning it should return a small, attribution‑diverse subset of valid models). These two axioms are not satisfied by most known attribution methods, which we consider to be a fundamental weakness. Building on these axioms, we propose an $\epsilon$-subgradient-based sampling framework and quantify effectiveness with Search Efficiency Ratio (SER) and Functional Explanation Range (FER). Experiments on a synthetic quadratic task and five real-world datasets show that our sampler achieves comparable or higher FER with up to $\\sim100\\times$ fewer models than exhaustive baselines such as TreeFARMS, while remaining agnostic to model class and loss. Even when the reference model is sub‑optimal in practice, the resulting attributions align with ground truth and accepted domain knowledge.