diff --git a/nifty/minimization/bare_dot.py b/nifty/minimization/bare_dot.py
new file mode 100644
index 0000000000000000000000000000000000000000..31e0864d4f0dc049acc5e965d88421fc9e263bb6
--- /dev/null
+++ b/nifty/minimization/bare_dot.py
@@ -0,0 +1,17 @@
+# -*- coding: utf-8 -*-
+
+import numpy as np
+
+
+def bare_dot(a, b):
+ try:
+ return a.dot(b, bare=True)
+ except(AttributeError, TypeError):
+ pass
+
+ try:
+ return a.vdot(b)
+ except(AttributeError):
+ pass
+
+ return np.vdot(a, b)
diff --git a/nifty/minimization/line_searching/line_search.py b/nifty/minimization/line_searching/line_search.py
index 7c0808019dd3051d46dc7b09fe79abd7acd4c9ea..169697512748ab1c2cd8f6b5c11b7e68adbe876e 100644
--- a/nifty/minimization/line_searching/line_search.py
+++ b/nifty/minimization/line_searching/line_search.py
@@ -1,22 +1,8 @@
import abc
-import numpy as np
-
from keepers import Loggable
-
-def bare_dot(a, b):
- try:
- return a.dot(b, bare=True)
- except(AttributeError, TypeError):
- pass
-
- try:
- return a.vdot(b)
- except(AttributeError):
- pass
-
- return np.vdot(a, b)
+from ..bare_dot import bare_dot
class LineSearch(object, Loggable):
@@ -78,8 +64,8 @@ class LineSearch(object, Loggable):
"""
- self.xk = xk
- self.pk = pk
+ self.xk = xk.copy()
+ self.pk = pk.copy()
if f_k is None:
self.f_k = self.f(xk)
@@ -91,6 +77,8 @@ class LineSearch(object, Loggable):
else:
self.fprime_k = fprime_k
+ if f_k_minus_1 is not None:
+ f_k_minus_1 = f_k_minus_1.copy()
self.f_k_minus_1 = f_k_minus_1
def _phi(self, alpha):
diff --git a/nifty/minimization/line_searching/line_search_strong_wolfe.py b/nifty/minimization/line_searching/line_search_strong_wolfe.py
index cb7098fa38d544e1985c4a416d59b7bb1e3b04f3..151c1e1300364fea8c8acdd977a054f7fa7a1143 100644
--- a/nifty/minimization/line_searching/line_search_strong_wolfe.py
+++ b/nifty/minimization/line_searching/line_search_strong_wolfe.py
@@ -10,7 +10,7 @@ class LineSearchStrongWolfe(LineSearch):
def __init__(self, c1=1e-4, c2=0.9,
max_step_size=50, max_iterations=10,
- max_zoom_iterations=100):
+ max_zoom_iterations=10):
"""
Parameters
@@ -82,7 +82,6 @@ class LineSearchStrongWolfe(LineSearch):
# start the minimization loop
for i in xrange(max_iterations):
phi_alpha1 = self._phi(alpha1)
-
if alpha1 == 0:
self.logger.warn("Increment size became 0.")
alpha_star = 0.
@@ -137,6 +136,10 @@ class LineSearchStrongWolfe(LineSearch):
cubic_delta = 0.2 # cubic
quad_delta = 0.1 # quadratic
+ cubic_delta = 0.0 # cubic
+ quad_delta = 0.0 # quadratic
+
+
# initialize the most recent versions (j-1) of phi and alpha
alpha_recent = 0
phi_recent = phi_0
diff --git a/nifty/minimization/quasi_newton_minimizer.py b/nifty/minimization/quasi_newton_minimizer.py
index 4a723d5352d51cfc70442f33b3444ed7f1e9686b..96915424953fcca0004f9ddb8c4b3ba58080fdc2 100644
--- a/nifty/minimization/quasi_newton_minimizer.py
+++ b/nifty/minimization/quasi_newton_minimizer.py
@@ -88,13 +88,14 @@ class QuasiNewtonMinimizer(object, Loggable):
# compute the step length, which minimizes f_k along the
# search direction = the gradient
- step_length, f_k = self.line_searcher.perform_line_search(
+ step_length, new_f_k = self.line_searcher.perform_line_search(
xk=x,
pk=descend_direction,
f_k=f_k,
fprime_k=gradient,
f_k_minus_1=f_k_minus_1)
f_k_minus_1 = f_k
+ f_k = new_f_k
# update x
x += descend_direction*step_length
@@ -106,7 +107,8 @@ class QuasiNewtonMinimizer(object, Loggable):
(iteration_number, step_length, delta))
if delta == 0:
convergence = self.convergence_level + 2
- self.logger.info("Found minimum. Stopping.")
+ self.logger.info("Found minimum according to line-search. "
+ "Stopping.")
break
elif delta < self.convergence_tolerance:
convergence += 1
diff --git a/nifty/minimization/vl_bfgs.py b/nifty/minimization/vl_bfgs.py
index bd5ed83dcb9d837c6892fbfe653756c3fed76d05..5cef3879e8c5f98cfbebf39a108bf7c708fdeff8 100644
--- a/nifty/minimization/vl_bfgs.py
+++ b/nifty/minimization/vl_bfgs.py
@@ -5,6 +5,8 @@ import numpy as np
from .quasi_newton_minimizer import QuasiNewtonMinimizer
from .line_searching import LineSearchStrongWolfe
+from .bare_dot import bare_dot
+
class VL_BFGS(QuasiNewtonMinimizer):
def __init__(self, line_searcher=LineSearchStrongWolfe(), callback=None,
@@ -20,6 +22,10 @@ class VL_BFGS(QuasiNewtonMinimizer):
self.max_history_length = max_history_length
+ def __call__(self, x0, f, fprime, f_args=()):
+ self._information_store = None
+ return super(VL_BFGS, self).__call__(x0, f, fprime, f_args=())
+
def _get_descend_direction(self, x, gradient):
# initialize the information store if it doesn't already exist
try:
@@ -36,6 +42,9 @@ class VL_BFGS(QuasiNewtonMinimizer):
for i in xrange(1, len(delta)):
descend_direction += delta[i] * b[i]
+ norm = np.sqrt(bare_dot(descend_direction, descend_direction))
+ if norm != 1:
+ descend_direction /= norm
return descend_direction
@@ -44,8 +53,8 @@ class InformationStore(object):
self.max_history_length = max_history_length
self.s = LimitedList(max_history_length)
self.y = LimitedList(max_history_length)
- self.last_x = x0
- self.last_gradient = gradient
+ self.last_x = x0.copy()
+ self.last_gradient = gradient.copy()
self.k = 0
self._ss_store = {}
@@ -168,8 +177,8 @@ class InformationStore(object):
new_y = gradient - self.last_gradient
self.y.add(new_y)
- self.last_x = x
- self.last_gradient = gradient
+ self.last_x = x.copy()
+ self.last_gradient = gradient.copy()
#
# k = self.k