rcognita.optimizers.GradientOptimizer

class rcognita.optimizers.GradientOptimizer(objective, learning_rate, N_steps, grad_norm_upper_bound=0.01, verbose=False)

__init__(objective, learning_rate, N_steps, grad_norm_upper_bound=0.01, verbose=False)

Initialize self. See help(type(self)) for accurate signature.

Methods

__init__(objective, learning_rate, N_steps)	Initialize self.
grad_step(initial_guess, *args)
optimize(*args, **kwargs)
substitute_args(initial_guess, *args)
verbose(opt_func)	A static method decorator that makes the decorated function verbose.

Attributes

engine