def _minimise_loss(self, X, y, lipschitz=None):
"""Use the FISTA algorithm to solve the group lasso regularised loss.
"""
if self.fit_intercept:
X = _add_intercept_col(X)
if lipschitz is None:
lipschitz = self._compute_lipschitz(X, y)
if not self.fit_intercept:
X = _add_intercept_col(X)
def grad(w):
g = self._grad(X, y, w)
if not self.fit_intercept:
g[0] = 0
return g
def prox(w):
b, w_ = _split_intercept(w)
w_ = _group_l2_prox(w_, self.reg_vector, self.groups_)
return _join_intercept(b, w_)
def loss(w):
X_, y_ = self.subsample(X, y)
self._loss(X_, y_, w)
def callback(x, it_num, previous_x=None):
X_, y_ = self.subsample(X, y)
w = x
previous_w = previous_x
self.losses_.append(self._loss(X_, y_, w))
if previous_w is None and _DEBUG:
print(f"Starting FISTA: ")
print(f"\tInitial loss: {self._loss(X_, y_, w)}")
elif _DEBUG:
print(f"Completed iteration {it_num}:")
print(f"\tLoss: {self._loss(X_, y_, w)}")
print(f"\tWeight difference: {la.norm(w-previous_w)}")
print(f"\tWeight norm: {la.norm(w)}")
print(f"\tGrad: {la.norm(grad(w))}")
weights = np.concatenate([self.intercept_, self.coef_])
weights = fista(
weights,
grad=grad,
prox=prox,
loss=loss,
lipschitz=lipschitz,
n_iter=self.n_iter,
tol=self.tol,
callback=callback,
)
self.intercept_, self.coef_ = _split_intercept(weights)
def _minimise_loss(self):
"""Use the FISTA algorithm to solve the group lasso regularised loss.
"""
# Need transition period before the correct regulariser is used without warning
def callback(x, it_num, previous_x=None):
X_, y_ = self.subsample(self.X_, self.y_)
w = x
previous_w = previous_x
if self.LOG_LOSSES:
self.losses_.append(self._loss(X_, y_, w))
if previous_w is None and _DEBUG: # pragma: nocover
print("Starting FISTA: ")
print("\tInitial loss: {loss}".format(
loss=self._loss(X_, y_, w)))
elif _DEBUG: # pragma: nocover
print("Completed iteration {it_num}:".format(it_num=it_num))
print("\tLoss: {loss}".format(loss=self._loss(X_, y_, w)))
print("\tWeight difference: {wdiff}".format(
wdiff=la.norm(w - previous_w)))
print("\tWeight norm: {wnorm}".format(wnorm=la.norm(w)))
print("\tGrad: {gnorm}".format(
gnorm=la.norm(self._unregularised_gradient(w))))
weights = np.concatenate([self.intercept_, self.coef_])
weights = fista(
weights,
grad=self._unregularised_gradient,
prox=self._scaled_prox,
loss=self._subsampled_loss,
lipschitz=self.lipschitz_,
n_iter=self.n_iter,
tol=self.tol,
callback=callback,
)
self.intercept_, self.coef_ = _split_intercept(weights)