def solve(self,
problem: Problem,
init_vars: np.ndarray = None,
show_process: bool = False):
if init_vars is None:
init_vars = np.random.rand(problem.dim)
self.reset()
start = time.time()
vars_current = init_vars
objv_current = problem.aim_func(vars_current)
grad_value = problem.cal_gradient(vars_current)
ng = np.linalg.norm(grad_value)
# record
self.cpu_time_arr.append(0)
self.f_value_arr.append(objv_current)
self.g_norm_arr.append(ng)
iter_count = 0
while ng > self.tol and iter_count < self.max_iter:
current = time.time()
# INNER STEP1: get d_k, use s_k or -grad_value
hessian = problem.cal_hessian(vars_current)
s_k = None
s_k_available = False
if (np.linalg.det(hessian) >= 1e-6): # invertible
s_k = -np.linalg.inv(hessian) @ grad_value
if -grad_value @ s_k >= min(
self.beta1, self.beta2 *
np.linalg.norm(s_k, self.p)) * np.linalg.norm(s_k)**2:
s_k_available = True
if s_k_available:
d_k = s_k
else:
d_k = -grad_value
# INNER STEP2: get a_k
alpha = self.s # initial alpha as self.s
objv_next = problem.aim_func(vars_current + alpha * d_k)
while np.isnan(objv_next) or (
(objv_next - objv_current) >
(self.gamma * alpha * grad_value @ d_k)):
alpha *= self.sigma
objv_next = problem.aim_func(vars_current + alpha * d_k)
vars_current = vars_current + alpha * d_k
objv_current = problem.aim_func(vars_current)
grad_value = problem.cal_gradient(vars_current)
ng = np.linalg.norm(grad_value)
iter_count += 1
if show_process:
print(f'iteration {iter_count} : {round(ng, 8)}', end=' ')
print(
f'time: {round(time.time() - current, 3)} second(self.s)')
# record
self.cpu_time_arr.append(time.time() - start)
self.f_value_arr.append(objv_current)
self.g_norm_arr.append(ng)
self.final_solution = vars_current
self.surface_points = problem.get_all_surface_points(vars_current)
return vars_current, grad_value, objv_current, ng, iter_count
def solve(self,
problem: Problem,
init_vars: np.ndarray = None,
show_process: bool = False):
if init_vars is None:
init_vars = np.random.rand(problem.dim)
self.reset()
start = time.time()
# Step1: calculate the gradient and its norm named 'ng'
vars_current = init_vars
grad_value = problem.cal_gradient(vars_current)
ng = np.linalg.norm(grad_value)
hessian = problem.cal_hessian(vars_current)
# ng_seq = []
# Step2: Iteration
objv_current = problem.aim_func(vars_current)
iter_count = 0
# Record
self.cpu_time_arr.append(0)
self.f_value_arr.append(objv_current)
self.g_norm_arr.append(ng)
while ng > self.tol and iter_count < self.max_iter:
current = time.time()
# INNER STEP1: get d_k
d_k = -grad_value
# INNER STEP2: get a_k
#alpha = self.s # initial alpha as s
alpha = -grad_value.T * d_k / (d_k.T @ hessian @ d_k)
# print(alpha)
vars_current = vars_current + alpha * d_k # Update vars
objv_current = problem.aim_func(vars_current)
grad_value = problem.cal_gradient(vars_current)
ng = np.linalg.norm(grad_value)
iter_count += 1
# ng_seq.append(ng)
if show_process:
print(f'iteration {iter_count} : {round(ng, 8)}', end=' ')
print(
f'time: {round(time.time() - current, 3)} second(self.s)')
self.cpu_time_arr.append(time.time() - start)
self.f_value_arr.append(objv_current)
self.g_norm_arr.append(ng)
self.final_solution = vars_current
self.surface_points = problem.get_all_surface_points(vars_current)
return vars_current, grad_value, objv_current, ng, iter_count
