nelder_mead()powell()
cg()
bfgs()
newton_cg()
l_bfgs_b(maxcor = 10, maxls = 20)
tnc(max_cg_it = -1, stepmx = 0, rescale = -1)
cobyla(rhobeg = 1)
slsqp()
gradient_descent(learning_rate = 0.01)
adadelta(learning_rate = 0.001, rho = 1, epsilon = 1e-08)
adagrad(learning_rate = 0.8, initial_accumulator_value = 0.1)
adagrad_da(learning_rate = 0.8, global_step = 1L,
initial_gradient_squared_accumulator_value = 0.1,
l1_regularization_strength = 0, l2_regularization_strength = 0)
momentum(learning_rate = 0.001, momentum = 0.9, use_nesterov = TRUE)
adam(learning_rate = 0.1, beta1 = 0.9, beta2 = 0.999,
epsilon = 1e-08)
ftrl(learning_rate = 1, learning_rate_power = -0.5,
initial_accumulator_value = 0.1, l1_regularization_strength = 0,
l2_regularization_strength = 0)
proximal_gradient_descent(learning_rate = 0.01,
l1_regularization_strength = 0, l2_regularization_strength = 0)
proximal_adagrad(learning_rate = 1, initial_accumulator_value = 0.1,
l1_regularization_strength = 0, l2_regularization_strength = 0)
rms_prop(learning_rate = 0.1, decay = 0.9, momentum = 0,
epsilon = 1e-10)