Evaluates a function from the IOHexperimenter Submodular problem class — a suite of submodular optimization problems on graphs, including Maximum Cut, Maximum Coverage, Maximum Influence, and Pack While Travel. All problems are binary maximization problems on {0, 1}^n.

1. Install uv if you don't have it yet:

pip install uv

No extra setup is needed beyond having uv installed. The ioh package is resolved automatically.

Note: This snippet requires Python 3.10. The inline metadata enforces this via requires-python = "==3.10". Make sure a Python 3.10 interpreter is available on your system.

uv run call_submodular_optimization.py

The script creates GRAPH problem 2000 (MaxCut), evaluates it at the all-zeros bitstring, and prints the result. You can adjust the behavior by editing these variables in the script:

• Problem ID — the first argument to ioh.get_problem() selects which problem to load (default: 2000)
• eval_point — the bitstring at which the function is evaluated (default: all zeros)

Note: GRAPH problems take integer inputs in {0, 1}^n (not floats). The dimensionality is determined by the problem (i.e. the underlying graph) and cannot be set manually.

• Submodular competition example notebook
• GECCO 2025 Evolutionary Submodular Optimisation Competition
• Benchmarking paper (Neumann et al.)
• IOHexperimenter GitHub repository