{ }
Update '*var' according to the proximal adagrad scheme.
tf.raw_ops.ApplyAdagradDA(
var,
gradient_accumulator,
gradient_squared_accumulator,
grad,
lr,
l1,
l2,
global_step,
use_locking=False,
name=None
)
Returns | |
---|---|
A mutable Tensor . Has the same type as var .
|