FrontierCO Algorithm Selection Model

Expert-calibrated algorithm selection model for the FrontierCO Solver Arena.

Inputs

9 structural instance features + problem type + size + difficulty + time budget.

Outputs

Head Description
solver_rank Ranked solver portfolio
predicted_gap Expected optimality gap (%)
predicted_runtime Expected wall-clock seconds
feasibility Predicted feasibility

Solver Portfolio

13 solvers across classical, metaheuristic, and neural families.

Related

Downloads last month
-
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Collection including alirezaaminzadeh/frontierco-selection-model