解释：def conjugate_gradient(fun, grad, x0, iterations, tol): """ Minimization of scalar function of one or more variables using the conjugate gradient algorithm. Parameters ---------- fun : function Objective function. grad : function Gradient function of objective function. x0 : numpy.array, size=9 Initial value of the parameters to be estimated. iterations : int Maximum iterations of optimization algorithms. tol : float Tolerance of optimization algorithms. Returns ------- xk : numpy.array, size=9 Parameters wstimated by optimization algorithms. fval : float Objective function value at xk. grad_val : float Gradient value of objective function at xk. grad_log : numpy.array The record of gradient of objective function of each iteration. """ fval = None grad_val = None x_log = [] y_log = [] grad_log = [] x0 = asarray(x0).flatten() # iterations = len(x0) * 200 old_fval = fun(x0) gfk = grad(x0) k = 0 xk = x0 # Sets the initial step guess to dx ~ 1 old_old_fval = old_fval + np.linalg.norm(gfk) / 2 pk = -gfk x_log = np.append(x_log, xk.T) y_log = np.append(y_log, fun(xk)) grad_log = np.append(grad_log, np.linalg.norm(xk - x_log[-1:])) gnorm = np.amax(np.abs(gfk)) sigma_3 = 0.01 while (gnorm > tol) and (k < iterations): deltak = np.dot(gfk, gfk) cached_step = [None] def polak_ribiere_powell_step(alpha, gfkp1=None): xkp1 = xk + alpha * pk if gfkp1 is None: gfkp1 = grad(xkp1) yk = gfkp1 - gfk beta_k = max(0, np.dot(yk, gfkp1) / deltak) pkp1 = -gfkp1 + beta_k * pk gnorm = np.amax(np.abs(gfkp1)) return (alpha, xkp1, pkp1, gfkp1, gnorm) def descent_condition(alpha, xkp1, fp1, gfkp1): # Polak-Ribiere+ needs an explicit check of a sufficient # descent condition, which is not guaranteed by strong Wolfe. # # See Gilbert & Nocedal, "Global convergence properties of # conjugate gradient methods for optimization", # SIAM J. Optimization 2, 21 (1992). cached_step[:] = polak_ribiere_powell_step(alpha, gfkp1) alpha, xk, pk, gfk, gnorm = cached_step # Accept step if it leads to convergence. if gnorm <= tol: return True # Accept step if sufficient descent condition applies. return np.dot(pk, gfk) <= -sigma_3 * np.dot(gfk, gfk) try: alpha_k, fc, gc, old_fval, old_old_fval, gfkp1 = \ _line_search_wolfe12(fun, grad, xk, pk, gfk, old_fval, old_old_fval, c2=0.4, amin=1e-100, amax=1e100, extra_condition=descent_condition) except _LineSearchError: break # Reuse already computed results if possible if alpha_k == cached_step[0]: alpha_k, xk, pk, gfk, gnorm = cached_step else: alpha_k, xk, pk, gfk, gnorm = polak_ribiere_powell_step(alpha_k, gfkp1) k += 1 grad_log = np.append(grad_log, np.linalg.norm(xk - x_log[-1:])) x_log = np.append(x_log, xk.T) y_log = np.append(y_log, fun(xk)) fval = old_fval grad_val = grad_log[-1] return xk, fval, grad_val, x_log, y_log, grad_log
2万+
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
