AdaBound¶
AdaBound optimizer.
Parameters¶
-
lr – defaults to
0.001The learning rate.
-
beta_1 – defaults to
0.9 -
beta_2 – defaults to
0.999 -
eps – defaults to
1e-08 -
gamma – defaults to
0.001 -
final_lr – defaults to
0.1
Attributes¶
-
m (collections.defaultdict)
-
s (collections.defaultdict)
Examples¶
>>> from river import datasets
>>> from river import evaluate
>>> from river import linear_model
>>> from river import metrics
>>> from river import optim
>>> from river import preprocessing
>>> dataset = datasets.Phishing()
>>> optimizer = optim.AdaBound()
>>> model = (
... preprocessing.StandardScaler() |
... linear_model.LogisticRegression(optimizer)
... )
>>> metric = metrics.F1()
>>> evaluate.progressive_val_score(dataset, model, metric)
F1: 87.90%
Methods¶
clone
Return a fresh estimator with the same parameters.
The clone has the same parameters but has not been updated with any data. This works by looking at the parameters from the class signature. Each parameter is either - recursively cloned if it's a River classes. - deep-copied via copy.deepcopy if not. If the calling object is stochastic (i.e. it accepts a seed parameter) and has not been seeded, then the clone will not be idempotent. Indeed, this method's purpose if simply to return a new instance with the same input parameters.
look_ahead
Updates a weight vector before a prediction is made.
Parameters: w (dict): A dictionary of weight parameters. The weights are modified in-place. Returns: The updated weights.
Parameters
- w (dict)
step
Updates a weight vector given a gradient.
Parameters
- w (Union[dict, river.utils.vectordict.VectorDict, numpy.ndarray])
- g (Union[dict, river.utils.vectordict.VectorDict, numpy.ndarray])
Returns
typing.Union[dict, river.utils.vectordict.VectorDict, numpy.ndarray]: The updated weights.