Optimizer¶
Optimizer interface.
Every optimizer inherits from this base interface.
Parameters¶
-
lr
Type → int | float | Scheduler
Attributes¶
-
learning_rate (float)
Returns the current learning rate value.
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.