Abstract This package offers a CMA-ES-based sampler with support for advanced restart strategies, specifically IPOP-CMA-ES and BIPOP-CMA-ES. Originally implemented in Optuna prior to v4.4.0, this functionality was removed to enhance the maintainability of Optuna’s core algorithms.
Please note that this sampler does not support CategoricalDistribution. However, optuna.distributions.FloatDistribution with step, (optuna.trial.Trial.suggest_float) and optuna.distributions.IntDistribution (optuna.trial.Trial.suggest_int) are supported.
If your search space contains categorical parameters, I recommend you to use optuna.samplers.TPESampler instead. Furthermore, there is room for performance improvements in parallel optimization settings.
APIs A sampler that uses Syne Tune v0.14.2 that can be run by the following:
$ pip install optunahub syne-tune Please check the API reference for more details:
https://syne-tune.readthedocs.io/en/latest/_apidoc/modules.html SyneTuneSampler(metric: str, search_space: dict[str, BaseDistribution], direction: str = "minimize", searcher_method: str = "CQR", searcher_kwargs: dict = None) search_space: A dictionary of Optuna distributions. direction: Defines direction of optimization. Must be one of the following: [minimize, maximize]. metric: The metric to be optimized.