SGD¶

Gradient descent (with momentum) optimizer.

Abstract Signature:

SGD(learning_rate: float = 0.01, momentum: float = 0.0, nesterov: boolean = False, weight_decay: float)

API: torch.optim.SGD

Strategy: Direct Mapping

API: optax.sgd

Strategy: Direct Mapping

API: keras.optimizers.SGD

Strategy: Direct Mapping

API: tf.keras.optimizers.SGD

Strategy: Direct Mapping

API: mlx.optimizers.SGD

Strategy: Direct Mapping

API: optax.sgd

Strategy: Direct Mapping