问为什么我的梯度下降算法不收敛？(用于Logistic回归)

EN

#include "armadillo.hpp"

using namespace arma;

double Log_Likelihood(Mat<double>& x, Mat<int>& y, Mat<double>& w)
    {
        Mat<double> L;
        double L_sum = 0;
        for (int i = 0; i < x.n_rows; i++)
        {
            L = log(1 + exp(-y[i] * w * x.row(i).t() ));
            L_sum += as_scalar(L);
        }

        return L_sum / x.n_rows;
    }

Mat<double> Gradient(Mat<double>& x, Mat<int>& y, Mat<double>& w)
    {
        Mat<double> grad(1, x.n_cols);
        for (int i = 0; i < x.n_rows; i++)
        {
            grad = grad + (y[i] * (1 / (1 + exp(y[i] * w * x.row(i).t()))) * x.row(i));
        }

        return -grad / x.n_rows;

    }

void fit(Mat<double>& x, Mat<int>& y, double alpha = 0.05, double threshold = pow(10, -7), int maxiter = 10000)
    {
        w.set_size(1, x.n_cols);
        w = x.row(0);
        int iter = 0;
        double log_like = 0;
        while (true)
        {
            log_like = Log_Likelihood(x, y, w);

            if (iter % 1000 == 0)
            {
                std::cout << "Iter: " << iter << " -Log likelihood = " << log_like << " ||dL/dw|| = " << norm( Gradient(x, y, w), 2) << std::endl;
            }
            iter++;

            if ( norm( Gradient(x, y, w), 2) < threshold)
            {
                std::cout << "Magnitude of gradient below threshold." << std::endl;
                break;
            }

            if (iter == maxiter)
            {
                std::cout << "Max iterations surpassed." << std::endl;
                break;
            }


            w = w - (alpha * Gradient(x, y, w));

        }
    }