LibMOON: A Gradient-based MultiObjective OptimizatioN Library in PyTorch

Multiobjective optimization problems (MOPs) are prevalent in machine learning, with applications in multi-task learning, fairness, robustness, and more. Unlike single-objective optimization, which aggregates objectives into a scalar through weighted sums, MOPs focus on generating specific or diverse Pareto solutions and learning the entire Pareto set directly. Existing MOP benchmarks primarily focus on evolutionary algorithms, which are zeroth-order or meta-heuristic methods that fail to leverage higher-order objective information and cannot scale to large models. To address these challenges, we introduce LibMOON, the first multiobjective optimization library supporting state-of-the-art gradient-based methods, offering a fair and comprehensive benchmark, and open-sourced for the community.