Skip to content

AMSGrad

AMSGrad optimizer.

Parameters

  • lr

    Typeint | float | optim.base.Scheduler

    Default0.1

    The learning rate.

  • beta_1

    Default0.9

  • beta_2

    Default0.999

  • eps

    Default1e-08

  • correct_bias

    DefaultTrue

Attributes

  • m (collections.defaultdict)

  • v (collections.defaultdict)

  • v_hat (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.AMSGrad()
model = (
    preprocessing.StandardScaler() |
    linear_model.LogisticRegression(optimizer)
)
metric = metrics.F1()

evaluate.progressive_val_score(dataset, model, metric)
F1: 86.60%

Methods

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'dict | VectorLike'
  • g'dict | VectorLike'

Returns

dict | VectorLike: The updated weights.