Adagrad

class viabel.Adagrad(learning_rate, *, weight_decay=0, jitter=1e-08, iterate_avg_prop=0.2, diagnostics=False)

Adagrad optimization method (Duchi et al., 2011)

Uses accumilated squared gradients to rescale the current stochastic gradient:

\[\frac{\hat{g}^{(k+1)}}{\sqrt{\sum^k_{k^\prime} \hat{g}^{(k^\prime)} \cdot \hat{g}^{(k^\prime)}}}\]

Parameters:

jitter: `float` optional

Small value used for numerical stability. The default is 1e-8

Returns:

descent_dirnumpy.ndarray, shape(var_param_dim,)

Descent direction of the optimization algorithm

Methods

descent_direction(grad)	Compute descent direction for optimization.
optimize(n_iters, objective, init_param[, ...])	Parameters:
reset_state()	restting accumilated squared gradient

__init__(learning_rate, *, weight_decay=0, jitter=1e-08, iterate_avg_prop=0.2, diagnostics=False)

Parameters:

learning_ratefloat

Tuning parameter that determines the step size

weight_decay: `float`

L2 regularization weight

iterate_avg_propfloat

Proportion of iterates to use for computing iterate average. None means no iterate averaging. The default is 0.2.

diagnosticsbool, optional

Record diagnostic information if True. The default is False.

descent_direction(grad)

Compute descent direction for optimization.

Default implementation returns grad.

Parameters:

gradnumpy.ndarray, shape(var_param_dim,)

(stochastic) gradient of the objective function

Returns:

descent_dirnumpy.ndarray, shape(var_param_dim,)

Descent direction of the optimization algorithm

reset_state()

restting accumilated squared gradient