def main() -> None:
# Generate solutions from a source task
source_solutions = []
for _ in range(1000):
x = np.random.random(2)
value = source_task(x[0], x[1])
source_solutions.append((x, value))
# Estimate a promising distribution of the source task
ws_mean, ws_sigma, ws_cov = get_warm_start_mgd(
source_solutions, gamma=0.1, alpha=0.1
)
optimizer = CMA(mean=ws_mean, sigma=ws_sigma, cov=ws_cov)
# Run WS-CMA-ES
print(" g f(x1,x2) x1 x2 ")
print("=== ========== ====== ======")
while True:
solutions = []
for _ in range(optimizer.population_size):
x = optimizer.ask()
value = target_task(x[0], x[1])
solutions.append((x, value))
print(
f"{optimizer.generation:3d} {value:10.5f}"
f" {x[0]:6.2f} {x[1]:6.2f}"
)
optimizer.tell(solutions)
if optimizer.should_stop():
break
def update(frame):
global solutions
for i in range(args.pop_per_frame):
x1 = (x1_upper_bound - x1_lower_bound) * rng.random() + x1_lower_bound
x2 = (x2_upper_bound - x2_lower_bound) * rng.random() + x2_lower_bound
evaluation = objective(x1, x2)
# Plot sample points
ax1.plot(x1, x2, "o", c="r", label="2d", alpha=0.5)
solution = (
np.array([x1, x2], dtype=float),
evaluation,
)
solutions.append(solution)
# Update title
fig.suptitle(
f"WS-CMA-ES {function_name} with alpha={args.alpha} and gamma={args.gamma} (frame={frame})"
)
# Plot multivariate gaussian distribution of CMA-ES
x, y = np.mgrid[x1_lower_bound:x1_upper_bound:0.01,
x2_lower_bound:x2_upper_bound:0.01]
if math.floor(len(solutions) * args.alpha) > 1:
mean, sigma, cov = get_warm_start_mgd(solutions,
alpha=args.alpha,
gamma=args.gamma)
rv = stats.multivariate_normal(mean, cov)
pos = np.dstack((x, y))
ax2.contourf(x, y, rv.pdf(pos))
if frame % 50 == 0:
print(f"Processing frame {frame}")
def _init_optimizer(
self,
trans: _SearchSpaceTransform,
direction: StudyDirection,
population_size: Optional[int] = None,
randomize_start_point: bool = False,
) -> CmaClass:
lower_bounds = trans.bounds[:, 0]
upper_bounds = trans.bounds[:, 1]
n_dimension = len(trans.bounds)
if self._source_trials is None:
if randomize_start_point:
mean = lower_bounds + (upper_bounds - lower_bounds
) * self._cma_rng.rand(n_dimension)
elif self._x0 is None:
mean = lower_bounds + (upper_bounds - lower_bounds) / 2
else:
# `self._x0` is external representations.
mean = trans.transform(self._x0)
if self._sigma0 is None:
sigma0 = np.min((upper_bounds - lower_bounds) / 6)
else:
sigma0 = self._sigma0
cov = None
else:
expected_states = [TrialState.COMPLETE]
if self._consider_pruned_trials:
expected_states.append(TrialState.PRUNED)
# TODO(c-bata): Filter parameters by their values instead of checking search space.
sign = 1 if direction == StudyDirection.MINIMIZE else -1
source_solutions = [
(trans.transform(t.params), sign * cast(float, t.value))
for t in self._source_trials if t.state in expected_states
and _is_compatible_search_space(trans, t.distributions)
]
if len(source_solutions) == 0:
raise ValueError("No compatible source_trials")
# TODO(c-bata): Add options to change prior parameters (alpha and gamma).
mean, sigma0, cov = get_warm_start_mgd(source_solutions)
# Avoid ZeroDivisionError in cmaes.
sigma0 = max(sigma0, _EPS)
if self._use_separable_cma:
return SepCMA(
mean=mean,
sigma=sigma0,
bounds=trans.bounds,
seed=self._cma_rng.randint(1, 2**31 - 2),
n_max_resampling=10 * n_dimension,
population_size=population_size,
)
return CMA(
mean=mean,
sigma=sigma0,
cov=cov,
bounds=trans.bounds,
seed=self._cma_rng.randint(1, 2**31 - 2),
n_max_resampling=10 * n_dimension,
population_size=population_size,
)
def test_dimension(self):
optimizer = CMA(mean=np.zeros(10), sigma=1.3)
source_solutions = [(optimizer.ask(), 0.0) for _ in range(100)]
ws_mean, ws_sigma, ws_cov = get_warm_start_mgd(source_solutions)
self.assertEqual(ws_mean.size, 10)