def grad_one_source(s, p_warm_start, p_grad_warm_start, w, training_data, params): (A, A_data) = edge_computation.compute_A(w, training_data["feature_stack"], training_data["edge_ij"], params["edge_strength_fun"], training_data["num_nodes"]) Q = edge_computation.compute_Q(A, A_data, training_data["edge_ij"], s, training_data["num_nodes"], params) Q_grad = [] for k in range(training_data["num_features"]): (df_dwk, df_dwk_data) = edge_computation.compute_df_dwk(k, training_data["feature_stack"], A_data, training_data["edge_ij"], params["edge_strength_grad_fun"], training_data["num_nodes"], params) dQ_dwk = edge_computation.compute_dQ_dwk(k, df_dwk, df_dwk_data, A, params, training_data["edge_ij"], A_data) Q_grad.append(dQ_dwk) (p_grad, p) = partial_gradient_update.update_p_grad(p_warm_start, p_grad_warm_start, Q, Q_grad, training_data["num_features"], params) dpprime_dp = compute_dpprime_dp(training_data, p) (p_prime, sum_p_candidates) = compute_p_prime(training_data, p) dpprime_dw = dpprime_dp.dot(p_grad) #Note: dpprime_dw is dense, even though it might have lots of zeros diff_generating_mat = training_data["diff_generating_mat"] diffs = diff_generating_mat.dot(p_prime) dpprime_dw_diffs = diff_generating_mat.dot(dpprime_dw) #This is (|L||D|) x num_features dh_ddiffs = params["h_grad_fun"](diffs, params["margin"]) #print(dpprime_dw_diffs) dh_dw = numpy.dot(dpprime_dw_diffs.T, dh_ddiffs) #print(dh_dw) return (dh_dw, p, p_grad)