AI RESEARCH

Proactive Routing to Interpretable Surrogates with Distribution-Free Safety Guarantees

arXiv CS.LG

ArXi:2603.14623v1 Announce Type: new Model routing determines whether to use an accurate black-box model or a simpler surrogate that approximates it at lower cost or greater interpretability. In deployment settings, practitioners often wish to restrict surrogate use to inputs where its degradation relative to a reference model is controlled. We study proactive (input-based) routing, in which a lightweight gate selects the model before either runs, enabling distribution-free control of the fraction of routed inputs whose degradation exceeds a tolerance {\tau.