/// <summary>
        /// Batch decomposition of the given matrix.
        /// The decomposed matrices can be retrieved via instance methods.
        /// </summary>
        /// <param name="arg">
        /// A rectangular matrix.
        /// </param>
        /// <param name="wantU">
        /// Whether the matrix U is needed.
        /// </param>
        /// <param name="wantV">
        /// Whether the matrix V is needed.
        /// </param>
        /// <param name="order">
        /// whether the singular values must be ordered.
        /// </param>
        /// <exception cref="ArgumentException">
        /// If
        /// <code>
        /// a.Rows &lt; a.Columns
        /// </code>
        /// .
        /// </exception>
        private void BatchSVD(DoubleMatrix2D arg, bool wantU, bool wantV, bool order)
        {
            Property.DEFAULT.CheckRectangular(arg);

            // Derived from LINPACK code.
            // Initialize.
            double[][] a = arg.ToArray();
            _m = arg.Rows;
            _n = arg.Columns;
            int nu = Math.Min(_m, _n);

            _s = new double[Math.Min(_m + 1, _n)];
            _u = new DenseDoubleMatrix2D(_m, nu);
            if (wantV)
            {
                _v = new DenseDoubleMatrix2D(_n, _n);
            }

            var e    = new double[_n];
            var work = new double[_m];

            // Reduce A to bidiagonal form, storing the diagonal elements
            // in s and the super-diagonal elements in e.
            int nct = Math.Min(_m - 1, _n);
            int nrt = Math.Max(0, Math.Min(_n - 2, _m));

            for (int k = 0; k < Math.Max(nct, nrt); k++)
            {
                if (k < nct)
                {
                    // Compute the transformation for the k-th column and
                    // place the k-th diagonal in s[k].
                    // Compute 2-norm of k-th column without under/overflow.
                    _s[k] = 0;
                    for (int i = k; i < _m; i++)
                    {
                        _s[k] = Algebra.Hypot(_s[k], a[i][k]);
                    }
                    if (_s[k] != 0.0)
                    {
                        if (a[k][k] < 0.0)
                        {
                            _s[k] = -_s[k];
                        }
                        for (int i = k; i < _m; i++)
                        {
                            a[i][k] /= _s[k];
                        }
                        a[k][k] += 1.0;
                    }

                    _s[k] = -_s[k];
                }

                for (int j = k + 1; j < _n; j++)
                {
                    if ((k < nct) & (_s[k] != 0.0))
                    {
                        // Apply the transformation.
                        double t = 0;
                        for (int i = k; i < _m; i++)
                        {
                            t += a[i][k] * a[i][j];
                        }
                        t = -t / a[k][k];
                        for (int i = k; i < _m; i++)
                        {
                            a[i][j] += t * a[i][k];
                        }
                    }

                    // Place the k-th row of A into e for the
                    // subsequent calculation of the row transformation.
                    e[j] = a[k][j];
                }

                if (wantU & (k < nct))
                {
                    // Place the transformation in U for subsequent back multiplication.
                    for (int i = k; i < _m; i++)
                    {
                        _u[i, k] = a[i][k];
                    }
                }

                if (k < nrt)
                {
                    // Compute the k-th row transformation and place the
                    // k-th super-diagonal in e[k].
                    // Compute 2-norm without under/overflow.
                    e[k] = 0;
                    for (int i = k + 1; i < _n; i++)
                    {
                        e[k] = Algebra.Hypot(e[k], e[i]);
                    }
                    if (e[k] != 0.0)
                    {
                        if (e[k + 1] < 0.0)
                        {
                            e[k] = -e[k];
                        }
                        for (int i = k + 1; i < _n; i++)
                        {
                            e[i] /= e[k];
                        }
                        e[k + 1] += 1.0;
                    }

                    e[k] = -e[k];
                    if ((k + 1 < _m) & (e[k] != 0.0))
                    {
                        // Apply the transformation.
                        for (int i = k + 1; i < _m; i++)
                        {
                            work[i] = 0.0;
                        }
                        for (int j = k + 1; j < _n; j++)
                        {
                            for (int i = k + 1; i < _m; i++)
                            {
                                work[i] += e[j] * a[i][j];
                            }
                        }

                        for (int j = k + 1; j < _n; j++)
                        {
                            double t = -e[j] / e[k + 1];
                            for (int i = k + 1; i < _m; i++)
                            {
                                a[i][j] += t * work[i];
                            }
                        }
                    }

                    if (wantV)
                    {
                        // Place the transformation in V for subsequent back multiplication.
                        for (int i = k + 1; i < _n; i++)
                        {
                            _v[i, k] = e[i];
                        }
                    }
                }
            }

            // Set up the final bidiagonal matrix or order p.
            int p = Math.Min(_n, _m + 1);

            if (nct < _n)
            {
                _s[nct] = a[nct][nct];
            }
            if (_m < p)
            {
                _s[p - 1] = 0.0;
            }
            if (nrt + 1 < p)
            {
                e[nrt] = a[nrt][p - 1];
            }
            e[p - 1] = 0.0;

            // If required, generate U.
            if (wantU)
            {
                for (int j = nct; j < nu; j++)
                {
                    for (int i = 0; i < _m; i++)
                    {
                        _u[i, j] = 0.0;
                    }
                    _u[j, j] = 1.0;
                }

                for (int k = nct - 1; k >= 0; k--)
                {
                    if (_s[k] != 0.0)
                    {
                        for (int j = k + 1; j < nu; j++)
                        {
                            double t = 0;
                            for (int i = k; i < _m; i++)
                            {
                                t += _u[i, k] * _u[i, j];
                            }
                            t = -t / _u[k, k];
                            for (int i = k; i < _m; i++)
                            {
                                _u[i, j] += t * _u[i, k];
                            }
                        }

                        for (int i = k; i < _m; i++)
                        {
                            _u[i, k] = -_u[i, k];
                        }
                        _u[k, k] = 1.0 + _u[k, k];
                        for (int i = 0; i < k - 1; i++)
                        {
                            _u[i, k] = 0.0;
                        }
                    }
                    else
                    {
                        for (int i = 0; i < _m; i++)
                        {
                            _u[i, k] = 0.0;
                        }
                        _u[k, k] = 1.0;
                    }
                }
            }

            // If required, generate V.
            if (wantV)
            {
                for (int k = _n - 1; k >= 0; k--)
                {
                    if ((k < nrt) & (e[k] != 0.0))
                    {
                        for (int j = k + 1; j < nu; j++)
                        {
                            double t = 0;
                            for (int i = k + 1; i < _n; i++)
                            {
                                t += _v[i, k] * _v[i, j];
                            }
                            t = -t / _v[k + 1, k];
                            for (int i = k + 1; i < _n; i++)
                            {
                                _v[i, j] += t * _v[i, k];
                            }
                        }
                    }

                    for (int i = 0; i < _n; i++)
                    {
                        _v[i, k] = 0.0;
                    }
                    _v[k, k] = 1.0;
                }
            }

            // Main iteration loop for the singular values.
            int    pp   = p - 1;
            int    iter = 0;
            double eps  = Math.Pow(2.0, -52.0);

            while (p > 0)
            {
                int k, kase;

                // Here is where a test for too many iterations would go.

                // This section of the program inspects for
                // negligible elements in the s and e arrays.  On
                // completion the variables kase and k are set as follows.

                // kase = 1     if s(p) and e[k-1] are negligible and k<p
                // kase = 2     if s(k) is negligible and k<p
                // kase = 3     if e[k-1] is negligible, k<p, and
                //              s(k), .., s(p) are not negligible (qr step).
                // kase = 4     if e(p-1) is negligible (convergence).
                for (k = p - 2; k >= -1; k--)
                {
                    if (k == -1)
                    {
                        break;
                    }
                    if (Math.Abs(e[k]) <= eps * (Math.Abs(_s[k]) + Math.Abs(_s[k + 1])))
                    {
                        e[k] = 0.0;
                        break;
                    }
                }

                if (k == p - 2)
                {
                    kase = 4;
                }
                else
                {
                    int ks;
                    for (ks = p - 1; ks >= k; ks--)
                    {
                        if (ks == k)
                        {
                            break;
                        }
                        double t = (ks != p ? Math.Abs(e[ks]) : 0) +
                                   (ks != k + 1 ? Math.Abs(e[ks - 1]) : 0);
                        if (Math.Abs(_s[ks]) <= eps * t)
                        {
                            _s[ks] = 0.0;
                            break;
                        }
                    }

                    if (ks == k)
                    {
                        kase = 3;
                    }
                    else if (ks == p - 1)
                    {
                        kase = 1;
                    }
                    else
                    {
                        kase = 2;
                        k    = ks;
                    }
                }

                k++;

                // Perform the task indicated by kase.
                switch (kase)
                {
                // Deflate negligible s(p).
                case 1:
                {
                    double f = e[p - 2];
                    e[p - 2] = 0.0;
                    for (int j = p - 2; j >= k; j--)
                    {
                        double t  = Algebra.Hypot(_s[j], f);
                        double cs = _s[j] / t;
                        double sn = f / t;
                        _s[j] = t;
                        if (j != k)
                        {
                            f        = -sn * e[j - 1];
                            e[j - 1] = cs * e[j - 1];
                        }

                        if (wantV)
                        {
                            for (int i = 0; i < _n; i++)
                            {
                                t            = (cs * _v[i, j]) + (sn * _v[i, p - 1]);
                                _v[i, p - 1] = -(sn * _v[i, j]) + (cs * _v[i, p - 1]);
                                _v[i, j]     = t;
                            }
                        }
                    }
                }

                break;

                // Split at negligible s(k).
                case 2:
                {
                    double f = e[k - 1];
                    e[k - 1] = 0.0;
                    for (int j = k; j < p; j++)
                    {
                        double t  = Algebra.Hypot(_s[j], f);
                        double cs = _s[j] / t;
                        double sn = f / t;
                        _s[j] = t;
                        f     = -sn * e[j];
                        e[j]  = cs * e[j];
                        if (wantU)
                        {
                            for (int i = 0; i < _m; i++)
                            {
                                t            = (cs * _u[i, j]) + (sn * _u[i, k - 1]);
                                _u[i, k - 1] = -(sn * _u[i, j]) + (cs * _u[i, k - 1]);
                                _u[i, j]     = t;
                            }
                        }
                    }
                }

                break;

                // Perform one qr step.
                case 3:
                {
                    // Calculate the shift.
                    double scale =
                        Math.Max(
                            Math.Max(
                                Math.Max(Math.Max(Math.Abs(_s[p - 1]), Math.Abs(_s[p - 2])), Math.Abs(e[p - 2])),
                                Math.Abs(_s[k])),
                            Math.Abs(e[k]));
                    double sp    = _s[p - 1] / scale;
                    double spm1  = _s[p - 2] / scale;
                    double epm1  = e[p - 2] / scale;
                    double sk    = _s[k] / scale;
                    double ek    = e[k] / scale;
                    double b     = (((spm1 + sp) * (spm1 - sp)) + (epm1 * epm1)) / 2.0;
                    double c     = (sp * epm1) * (sp * epm1);
                    double shift = 0.0;
                    if ((b != 0.0) | (c != 0.0))
                    {
                        shift = Math.Sqrt((b * b) + c);
                        if (b < 0.0)
                        {
                            shift = -shift;
                        }
                        shift = c / (b + shift);
                    }

                    double f = ((sk + sp) * (sk - sp)) + shift;
                    double g = sk * ek;

                    // Chase zeros.
                    for (int j = k; j < p - 1; j++)
                    {
                        double t  = Algebra.Hypot(f, g);
                        double cs = f / t;
                        double sn = g / t;
                        if (j != k)
                        {
                            e[j - 1] = t;
                        }
                        f         = (cs * _s[j]) + (sn * e[j]);
                        e[j]      = (cs * e[j]) - (sn * _s[j]);
                        g         = sn * _s[j + 1];
                        _s[j + 1] = cs * _s[j + 1];
                        if (wantV)
                        {
                            for (int i = 0; i < _n; i++)
                            {
                                t            = (cs * _v[i, j]) + (sn * _v[i, j + 1]);
                                _v[i, j + 1] = -(sn * _v[i, j]) + (cs * _v[i, j + 1]);
                                _v[i, j]     = t;
                            }
                        }

                        t         = Algebra.Hypot(f, g);
                        cs        = f / t;
                        sn        = g / t;
                        _s[j]     = t;
                        f         = (cs * e[j]) + (sn * _s[j + 1]);
                        _s[j + 1] = -(sn * e[j]) + (cs * _s[j + 1]);
                        g         = sn * e[j + 1];
                        e[j + 1]  = cs * e[j + 1];
                        if (wantU && (j < _m - 1))
                        {
                            for (int i = 0; i < _m; i++)
                            {
                                t            = (cs * _u[i, j]) + (sn * _u[i, j + 1]);
                                _u[i, j + 1] = -(sn * _u[i, j]) + (cs * _u[i, j + 1]);
                                _u[i, j]     = t;
                            }
                        }
                    }

                    e[p - 2] = f;
                    iter     = iter + 1;
                }

                break;

                // Convergence.
                case 4:
                {
                    // Make the singular values positive.
                    if (_s[k] <= 0.0)
                    {
                        _s[k] = _s[k] < 0.0 ? -_s[k] : 0.0;
                        if (wantV)
                        {
                            for (int i = 0; i <= pp; i++)
                            {
                                _v[i, k] = -_v[i, k];
                            }
                        }
                    }

                    // Order the singular values.
                    if (order)
                    {
                        while (k < pp)
                        {
                            if (_s[k] >= _s[k + 1])
                            {
                                break;
                            }
                            double t = _s[k];
                            _s[k]     = _s[k + 1];
                            _s[k + 1] = t;
                            if (wantV && (k < _n - 1))
                            {
                                for (int i = 0; i < _n; i++)
                                {
                                    t            = _v[i, k + 1];
                                    _v[i, k + 1] = _v[i, k];
                                    _v[i, k]     = t;
                                }
                            }

                            if (k < _m - 1)
                            {
                                for (int i = 0; i < _m; i++)
                                {
                                    t            = _u[i, k + 1];
                                    _u[i, k + 1] = _u[i, k];
                                    _u[i, k]     = t;
                                }
                            }

                            k++;
                        }
                    }

                    iter = 0;
                    p--;
                }

                break;
                }
            }
        }