Provably Data-driven Multiple Hyper-parameter Tuning with Structured Loss Function

ArXi:2602.02406v2 Announce Type: replace-cross Data-driven algorithm design automates hyperparameter tuning, but its statistical foundations remain limited because model performance can depend on hyperparameters in implicit and highly non-smooth ways. Existing guarantees focus on the simple case of a one-dimensional (scalar) hyperparameter. This leaves the practically important, multi-dimensional hyperparameter tuning setting unresolved.