ray.tune.search.zoopt.ZOOptSearch#

class ray.tune.search.zoopt.ZOOptSearch(algo: str = 'asracos', budget: int | None = None, dim_dict: Dict | None = None, metric: str | None = None, mode: str | None = None, points_to_evaluate: List[Dict] | None = None, parallel_num: int = 1, **kwargs)[source]#

Bases: Searcher

A wrapper around ZOOpt to provide trial suggestions.

ZOOptSearch is a library for derivative-free optimization. It is backed by the ZOOpt package. Currently, Asynchronous Sequential RAndomized COordinate Shrinking (ASRacos) is implemented in Tune.

To use ZOOptSearch, install zoopt (>=0.4.1): pip install -U zoopt.

Tune automatically converts search spaces to ZOOpt”s format:

from ray import tune
from ray.tune.search.zoopt import ZOOptSearch

"config": {
    "iterations": 10,  # evaluation times
    "width": tune.uniform(-10, 10),
    "height": tune.uniform(-10, 10)
}

zoopt_search_config = {
    "parallel_num": 8,  # how many workers to parallel
}

zoopt_search = ZOOptSearch(
    algo="Asracos",  # only support Asracos currently
    budget=20,  # must match `num_samples` in `tune.TuneConfig()`.
    dim_dict=dim_dict,
    metric="mean_loss",
    mode="min",
    **zoopt_search_config
)

tuner = tune.Tuner(
    my_objective,
    tune_config=tune.TuneConfig(
        search_alg=zoopt_search,
        num_samples=20
    ),
    run_config=tune.RunConfig(
        name="zoopt_search",
        stop={"timesteps_total": 10}
    ),
    param_space=config
)
tuner.fit()

If you would like to pass the search space manually, the code would look like this:

from ray import tune
from ray.tune.search.zoopt import ZOOptSearch
from zoopt import ValueType

dim_dict = {
    "height": (ValueType.CONTINUOUS, [-10, 10], 1e-2),
    "width": (ValueType.DISCRETE, [-10, 10], False),
    "layers": (ValueType.GRID, [4, 8, 16])
}

"config": {
    "iterations": 10,  # evaluation times
}

zoopt_search_config = {
    "parallel_num": 8,  # how many workers to parallel
}

zoopt_search = ZOOptSearch(
    algo="Asracos",  # only support Asracos currently
    budget=20,  # must match `num_samples` in `tune.TuneConfig()`.
    dim_dict=dim_dict,
    metric="mean_loss",
    mode="min",
    **zoopt_search_config
)

tuner = tune.Tuner(
    my_objective,
    tune_config=tune.TuneConfig(
        search_alg=zoopt_search,
        num_samples=20
    ),
    run_config=tune.RunConfig(
        name="zoopt_search",
        stop={"timesteps_total": 10}
    ),
)
tuner.fit()

Parameters:

algo – To specify an algorithm in zoopt you want to use. Only support ASRacos currently.
budget – Number of samples.
dim_dict – Dimension dictionary. For continuous dimensions: (continuous, search_range, precision); For discrete dimensions: (discrete, search_range, has_order); For grid dimensions: (grid, grid_list). More details can be found in zoopt package.
metric – The training result objective value attribute. If None but a mode was passed, the anonymous metric _metric will be used per default.
mode – One of {min, max}. Determines whether objective is minimizing or maximizing the metric attribute.
points_to_evaluate – Initial parameter suggestions to be run first. This is for when you already have some good parameters you want to run first to help the algorithm make better suggestions for future parameters. Needs to be a list of dicts containing the configurations.
parallel_num – How many workers to parallel. Note that initial phase may start less workers than this number. More details can be found in zoopt package.

Methods

`add_evaluated_point`	Pass results from a point that has been evaluated separately.
`add_evaluated_trials`	Pass results from trials that have been evaluated separately.
`on_trial_complete`	Notification for the completion of trial.
`on_trial_result`	Optional notification for result during training.
`restore_from_dir`	Restores the state of a searcher from a given checkpoint_dir.
`save_to_dir`	Automatically saves the given searcher to the checkpoint_dir.
`set_max_concurrency`	Set max concurrent trials this searcher can run.

Attributes

`CKPT_FILE_TMPL`
`FINISHED`
`metric`	The training result objective value attribute.
`mode`	Specifies if minimizing or maximizing the metric.
`optimizer`