def primal_loss(w_vect, reg, i_primal, record_results=False): RS = RandomState((seed, i_primal, "primal")) idxs = RS.randint(N_data, size=batch_size) minibatch = dictslice(data, idxs) loss = loss_fun(w_vect, **minibatch) reg = regularization(w_vect, reg) if record_results and i_primal % N_thin == 0: print "Iter {0}: train: {1}".format(i_primal, getval(loss)) return loss + reg
def new_hyperloss(reg, i_hyper, cur_train_data, cur_valid_data): RS = RandomState((seed, i_hyper, "hyperloss")) w_vect_0 = RS.randn(N_weights) * init_scales w_vect_final = train_z(loss_fun, cur_train_data, w_vect_0, reg) return loss_fun(w_vect_final, **cur_valid_data)