# HG changeset patch
# User James Bergstra <bergstrj@iro.umontreal.ca>
# Date 1282310879 14400
# Node ID 8e78afa74313c8a6be452c6db2590f587c26b44d
# Parent  a0a6cc21dc4fccff00922e9365379599aaf85bf4
Moved sgd to gd/ module

diff -r a0a6cc21dc4f -r 8e78afa74313 pylearn/algorithms/sgd.py
--- a/pylearn/algorithms/sgd.py	Thu Aug 19 14:44:15 2010 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,75 +0,0 @@
-"""A stochastic gradient descent minimizer. (Possibly the simplest minimizer.)
-"""
-
-import theano
-
-class StochasticGradientDescent(theano.Module):
-    """Fixed stepsize gradient descent
-
-    Methods for gradient descent are:
-    - step(arg_vals) which returns None and updates the params
-    - step_cost(arg_vals) which returns the cost value, and updates the params
-    
-    """
-    def __init__(self, args, cost, params, 
-                 gradients=None, stepsize=None, 
-                 updates=None, auxout=None, methods=True):
-        """
-        :param stepsize: the step to take in (negative) gradient direction
-        :type stepsize: None, scalar value, or scalar TensorVariable
-
-        :param updates: extra symbolic updates to make when evating either step or step_cost
-        (these override the gradients if necessary)
-        :type updates: dict Variable -> Variable
-        :param auxout: auxiliary outputs, list containing output symbols to 
-                      compute at the same time as cost (for efficiency)
-        :param methods: Should this module define the step and step_cost methods?
-        """
-        super(StochasticGradientDescent, self).__init__()
-        self.stepsize_init = None
-
-        if stepsize is None:
-            self.stepsize = theano.tensor.dscalar()
-        elif isinstance(stepsize, theano.tensor.TensorVariable):
-            self.stepsize = stepsize
-        else:
-            self.stepsize = (theano.tensor.as_tensor_variable(stepsize))
-
-        if self.stepsize.ndim != 0:
-            raise TypeError('stepsize must be a scalar', stepsize)
-
-        self.params = params
-        self.gparams = theano.tensor.grad(cost, self.params) if gradients is None else gradients
-
-        self._updates = (dict((p, p - self.stepsize * g) for p, g in zip(self.params, self.gparams)))
-        if updates is not None:
-            self._updates.update(updates)
-
-        if methods:
-            if auxout is None:
-                self.step = theano.Method(args, [], updates=self._updates)
-                self.step_cost = theano.Method(args, cost, updates=self._updates)
-            else:
-                # step cost always returns a list if auxout
-                self.step = theano.Method(
-                        args, [] + auxout,
-                        updates=self._updates)
-                self.step_cost = theano.Method(
-                        args, [cost]+auxout,
-                        updates=self._updates)
-
-
-    updates = property(lambda self: self._updates.copy())
-
-    def _instance_initialize(self, obj):
-        pass
-
-def sgd_minimizer(stepsize=None):
-    """Curry the stepsize argument to StochasticGradientDescent, providing standard minimizer interface
-    
-    :returns: standard minimizer constructor f(args, cost, params, gradient=None)
-    """
-    def f(args, cost, params, gradients=None, updates=None, auxout=None):
-        return StochasticGradientDescent(args, cost, params, gradients=gradients, stepsize=stepsize,
-                updates=updates, auxout=auxout)
-    return f
diff -r a0a6cc21dc4f -r 8e78afa74313 pylearn/algorithms/tests/test_sgd.py
--- a/pylearn/algorithms/tests/test_sgd.py	Thu Aug 19 14:44:15 2010 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,75 +0,0 @@
-import theano
-from theano.compile.debugmode import DebugMode
-from pylearn.algorithms import sgd
-
-mode = theano.compile.mode.get_default_mode()
-if isinstance(mode,DebugMode):
-    mode = 'FAST_RUN'
-
-def test_sgd0():
-
-    x = theano.tensor.dscalar('x')
-    y = theano.tensor.dscalar('y')
-
-    M = sgd.StochasticGradientDescent([x], (1.0 - x * y)**2, [y], stepsize=0.01)
-    M.y = y
-    m = M.make(mode=mode)
-    m.y = 5.0
-    for i in xrange(100):
-        c = m.step_cost(3.0)
-        #print c[0], m.y
-
-    assert c < 1.0e-5
-    assert abs(m.y - (1.0 / 3)) < 1.0e-4
-
-def test_sgd_stepsize_variable():
-
-    x = theano.tensor.dscalar('x')
-    y = theano.tensor.dscalar('y')
-    lr = theano.tensor.dscalar('lr')
-
-    M = sgd.StochasticGradientDescent([x], (1.0 - x * y)**2, [y], stepsize=lr)
-    M.y = y
-    M.lr = lr
-    m = M.make(mode=mode)
-    m.y = 5.0
-    m.lr = 0.01
-    for i in xrange(100):
-        c = m.step_cost(3.0)
-        # print c, m.y
-
-    assert c < 1.0e-5
-    assert abs(m.y - (1.0 / 3)) < 1.0e-4
-
-
-    #test that changing the lr has impact
-
-    m.y = 5.0
-    m.lr = 0.0
-    for i in xrange(10):
-        c = m.step_cost(3.0)
-        # print c, m.y
-
-    assert m.y == 5.0
-
-def test_sgd_stepsize_none():
-
-    x = theano.tensor.dscalar('x')
-    y = theano.tensor.dscalar('y')
-
-    M = sgd.StochasticGradientDescent([x], (1.0 - x * y)**2, [y])
-    M.y = y
-    m = M.make(mode=mode)
-    m.y = 5.0
-    #there should be a learning rate here by default
-    assert m.stepsize is None
-    m.stepsize = 0.01
-    for i in xrange(100):
-        c = m.step_cost(3.0)
-        # print c, m.y
-
-    assert c < 1.0e-5
-    assert abs(m.y - (1.0 / 3)) < 1.0e-4
-
-if __name__ == '__main__':
-    test_sgd0()