gradient – Symbolic Differentiation

Symbolic gradient is usually computed from gradient.grad(), which offers a more convenient syntax for the common case of wanting the gradient of some scalar cost with respect to some input expressions. The grad_sources_inputs() function does the underlying work, and is more flexible, but is also more awkward to use when gradient.grad() can do the job.

Gradient related functions

Driver for gradient calculations.

exception theano.gradient.DisconnectedInputError[source]

Raised when grad is asked to compute the gradient with respect to a disconnected input and disconnected_inputs=’raise’.

class theano.gradient.DisconnectedType[source]

A type indicating that a variable is a result of taking the gradient of c with respect to x when c is not a function of x. A symbolic placeholder for 0, but to convey the extra information that this gradient is 0 because it is disconnected.

exception theano.gradient.GradientError(arg, err_pos, shape, val1, val2, abs_err, rel_err, abs_tol, rel_tol)[source]

This error is raised when a gradient is calculated, but incorrect.

theano.gradient.Lop(f, wrt, eval_points, consider_constant=None, disconnected_inputs='raise')[source]

Computes the L operation on f wrt to wrt at eval_points.

Mathematically this stands for the jacobian of f wrt to wrt left muliplied by the eval points.

Parameters:
  • f (Variable or list of Variables) – f stands for the output of the computational graph to which you want to apply the L operator
  • wrt (Variable or list of Variables) – variables for which you compute the L operator of the expression described by f
  • eval_points (Variable or list of Variables) – evalutation points for each of the variables in f
Returns:

Symbolic expression such that L_op[i] = sum_i (d f[i] / d wrt[j]) eval_point[i] where the indices in that expression are magic multidimensional indices that specify both the position within a list and all coordinates of the tensor element in the last If f is a list/tuple, then return a list/tuple with the results.

Return type:

Variable or list/tuple of Variables depending on type of f

exception theano.gradient.NullTypeGradError[source]

Raised when grad encounters a NullType.

theano.gradient.Rop(f, wrt, eval_points, disconnected_outputs='raise', return_disconnected='zero')[source]

Computes the R operation on f wrt to wrt at eval_points.

Mathematically this stands for the jacobian of f wrt to wrt right muliplied by the eval points.

Parameters:
  • f (Variable or list of Variables) – f stands for the output of the computational graph to which you want to apply the R operator
  • wrt (Variable or list of Variables) – variables for which you compute the R operator of the expression described by f
  • eval_points (Variable or list of Variables) – evalutation points for each of the variables in wrt
  • disconnected_outputs (str) –

    Defines the behaviour if some of the variables in f have no dependency on any of the variable in wrt (or if all links are non-differentiable). The possible values are:

    • ‘ignore’: considers that the gradient on these parameters is zero.
    • ‘warn’: consider the gradient zero, and print a warning.
    • ‘raise’: raise DisconnectedInputError.
  • return_disconnected ({'zero', 'None', 'Disconnected'}) –
    • ‘zero’ : If wrt[i] is disconnected, return value i will be wrt[i].zeros_like()
    • ‘None’ : If wrt[i] is disconnected, return value i will be None
    • ‘Disconnected’ : returns variables of type DisconnectedType
Returns:

Symbolic expression such that R_op[i] = sum_j (d f[i] / d wrt[j]) eval_point[j] where the indices in that expression are magic multidimensional indices that specify both the position within a list and all coordinates of the tensor element in the last. If wrt is a list/tuple, then return a list/tuple with the results.

Return type:

Variable or list/tuple of Variables depending on type of f

theano.gradient.consider_constant(x)[source]

DEPRECATED: use zero_grad() or disconnected_grad() instead.

Consider an expression constant when computing gradients.

The expression itself is unaffected, but when its gradient is computed, or the gradient of another expression that this expression is a subexpression of, it will not be backpropagated through. In other words, the gradient of the expression is truncated to 0.

Parameters:x – A Theano expression whose gradient should be truncated.
Returns:The expression is returned unmodified, but its gradient is now truncated to 0.

New in version 0.7.

theano.gradient.disconnected_grad(x)[source]

Consider an expression constant when computing gradients.

It will effectively not backpropagating through it.

The expression itself is unaffected, but when its gradient is computed, or the gradient of another expression that this expression is a subexpression of, it will not be backpropagated through. This is effectively equivalent to truncating the gradient expression to 0, but is executed faster than zero_grad(), which stilll has to go through the underlying computational graph related to the expression.

Parameters:x (Variable) – A Theano expression whose gradient should not be backpropagated through.
Returns:An expression equivalent to x, with its gradient now effectively truncated to 0.
Return type:Variable
theano.gradient.format_as(use_list, use_tuple, outputs)[source]

Formats the outputs according to the flags use_list and use_tuple.

If use_list is True, outputs is returned as a list (if outputs is not a list or a tuple then it is converted in a one element list). If use_tuple is True, outputs is returned as a tuple (if outputs is not a list or a tuple then it is converted into a one element tuple). Otherwise (if both flags are false), outputs is returned.

theano.gradient.grad(cost, wrt, consider_constant=None, disconnected_inputs='raise', add_names=True, known_grads=None, return_disconnected='zero', null_gradients='raise')[source]

Return symbolic gradients of one cost with respect to one or more variables.

For more information about how automatic differentiation works in Theano, see gradient. For information on how to implement the gradient of a certain Op, see grad().

Parameters:
  • cost (Variable scalar (0-dimensional) tensor variable or None) – Value that we are differentiating (that we want the gradient of). May be None if known_grads is provided.
  • wrt (Variable or list of Variables) – Term[s] with respect to which we want gradients
  • consider_constant (list of variables) – Expressions not to backpropagate through
  • disconnected_inputs ({'ignore', 'warn', 'raise'}) –

    Defines the behaviour if some of the variables in wrt are not part of the computational graph computing cost (or if all links are non-differentiable). The possible values are:

    • ‘ignore’: considers that the gradient on these parameters is zero.
    • ‘warn’: consider the gradient zero, and print a warning.
    • ‘raise’: raise DisconnectedInputError.
  • add_names (bool) – If True, variables generated by grad will be named (d<cost.name>/d<wrt.name>) provided that both cost and wrt have names
  • known_grads (OrderedDict, optional) – A ordered dictionary mapping variables to their gradients. This is useful in the case where you know the gradient on some variables but do not know the original cost.
  • return_disconnected ({'zero', 'None', 'Disconnected'}) –
    • ‘zero’ : If wrt[i] is disconnected, return value i will be wrt[i].zeros_like()
    • ‘None’ : If wrt[i] is disconnected, return value i will be None
    • ‘Disconnected’ : returns variables of type DisconnectedType
  • null_gradients ({'raise', 'return'}) –

    Defines the behaviour if some of the variables in wrt have a null gradient. The possibles values are:

    • ‘raise’ : raise a NullTypeGradError exception
    • ‘return’ : return the null gradients
Returns:

Symbolic expression of gradient of cost with respect to each of the wrt terms. If an element of wrt is not differentiable with respect to the output, then a zero variable is returned.

Return type:

variable or list/tuple of variables (matches wrt)

theano.gradient.grad_clip(x, lower_bound, upper_bound)[source]

This op do a view in the forward, but clip the gradient.

This is an elemwise operation.

Parameters:
  • x – The variable we want its gradient inputs clipped
  • lower_bound – The lower bound of the gradient value
  • upper_bound – The upper bound of the gradient value.

Examples

>>> x = theano.tensor.scalar()
>>> z = theano.tensor.grad(grad_clip(x, -1, 1)**2, x)
>>> z2 = theano.tensor.grad(x**2, x)
>>> f = theano.function([x], outputs = [z, z2])
>>> print(f(2.0))
[array(1.0), array(4.0)]

Note

We register an opt in tensor/opt.py that remove the GradClip. So it have 0 cost in the forward and only do work in the grad.

theano.gradient.grad_not_implemented(op, x_pos, x, comment='')[source]

Return an un-computable symbolic variable of type x.type.

If any call to tensor.grad results in an expression containing this un-computable variable, an exception (NotImplementedError) will be raised indicating that the gradient on the x_pos‘th input of op has not been implemented. Likewise if any call to theano.function involves this variable.

Optionally adds a comment to the exception explaining why this gradient is not implemented.

theano.gradient.grad_scale(x, multiplier)[source]

This op scale or inverse the gradient in the backpropagation.

Parameters:
  • x – The variable we want its gradient inputs scale
  • multiplier – Scale of the gradient

Examples

>>> x = theano.tensor.fscalar()
>>> fx = theano.tensor.sin(x)
>>> fp = theano.tensor.grad(fx, wrt=x)
>>> fprime = theano.function([x], fp)
>>> print(fprime(2))  
-0.416...
>>> f_inverse=grad_scale(fx, -1.)
>>> fpp = theano.tensor.grad(f_inverse, wrt=x)
>>> fpprime = theano.function([x], fpp)
>>> print(fpprime(2))  
0.416...
theano.gradient.grad_undefined(op, x_pos, x, comment='')[source]

Return an un-computable symbolic variable of type x.type.

If any call to tensor.grad results in an expression containing this un-computable variable, an exception (GradUndefinedError) will be raised indicating that the gradient on the x_pos‘th input of op is mathematically undefined. Likewise if any call to theano.function involves this variable.

Optionally adds a comment to the exception explaining why this gradient is not defined.

theano.gradient.hessian(cost, wrt, consider_constant=None, disconnected_inputs='raise')[source]
Parameters:
  • cost (Scalar (0-dimensional) variable.) –
  • wrt (Vector (1-dimensional tensor) 'Variable' or list of) –
  • (1-dimensional tensors) Variables (vectors) –
  • consider_constant – a list of expressions not to backpropagate through
  • disconnected_inputs (string) –

    Defines the behaviour if some of the variables in wrt are not part of the computational graph computing cost (or if all links are non-differentiable). The possible values are:

    • ‘ignore’: considers that the gradient on these parameters is zero.
    • ‘warn’: consider the gradient zero, and print a warning.
    • ‘raise’: raise an exception.
Returns:

The Hessian of the cost with respect to (elements of) wrt. If an element of wrt is not differentiable with respect to the output, then a zero variable is returned. The return value is of same type as wrt: a list/tuple or TensorVariable in all cases.

Return type:

Variable or list/tuple of Variables

theano.gradient.jacobian(expression, wrt, consider_constant=None, disconnected_inputs='raise')[source]

Compute the full Jacobian, row by row.

Parameters:
  • expression (Vector (1-dimensional) Variable) – Values that we are differentiating (that we want the Jacobian of)
  • wrt (Variable or list of Variables) – Term[s] with respect to which we compute the Jacobian
  • consider_constant (list of variables) – Expressions not to backpropagate through
  • disconnected_inputs (string) –

    Defines the behaviour if some of the variables in wrt are not part of the computational graph computing cost (or if all links are non-differentiable). The possible values are:

    • ‘ignore’: considers that the gradient on these parameters is zero.
    • ‘warn’: consider the gradient zero, and print a warning.
    • ‘raise’: raise an exception.
Returns:

The Jacobian of expression with respect to (elements of) wrt. If an element of wrt is not differentiable with respect to the output, then a zero variable is returned. The return value is of same type as wrt: a list/tuple or TensorVariable in all cases.

Return type:

Variable or list/tuple of Variables (depending upon wrt)

class theano.gradient.numeric_grad(f, pt, eps=None, out_type=None)[source]

Compute the numeric derivative of a scalar-valued function at a particular point.

static abs_rel_err(a, b)[source]

Return absolute and relative error between a and b.

The relative error is a small number when a and b are close, relative to how big they are.

Formulas used:

abs_err = abs(a - b)

rel_err = abs_err / max(abs(a) + abs(b), 1e-8)

The denominator is clipped at 1e-8 to avoid dividing by 0 when a and b are both close to 0.

The tuple (abs_err, rel_err) is returned

abs_rel_errors(g_pt)[source]

Return the abs and rel error of gradient estimate g_pt

g_pt must be a list of ndarrays of the same length as self.gf, otherwise a ValueError is raised.

Corresponding ndarrays in g_pt and self.gf must have the same shape or ValueError is raised.

max_err(g_pt, abs_tol, rel_tol)[source]

Find the biggest error between g_pt and self.gf.

What is measured is the violation of relative and absolute errors, wrt the provided tolerances (abs_tol, rel_tol). A value > 1 means both tolerances are exceeded.

Return the argmax of min(abs_err / abs_tol, rel_err / rel_tol) over g_pt, as well as abs_err and rel_err at this point.

theano.gradient.subgraph_grad(wrt, end, start=None, cost=None, details=False)[source]

With respect to wrt, computes gradients of cost and/or from existing start gradients, up to the end variables of a symbolic digraph. In other words, computes gradients for a subgraph of the symbolic theano function. Ignores all disconnected inputs.

This can be useful when one needs to perform the gradient descent iteratively (e.g. one layer at a time in an MLP), or when a particular operation is not differentiable in theano (e.g. stochastic sampling from a multinomial). In the latter case, the gradient of the non-differentiable process could be approximated by user-defined formula, which could be calculated using the gradients of a cost with respect to samples (0s and 1s). These gradients are obtained by performing a subgraph_grad from the cost or previously known gradients (start) up to the outputs of the stochastic process (end). A dictionary mapping gradients obtained from the user-defined differentiation of the process, to variables, could then be fed into another subgraph_grad as start with any other cost (e.g. weight decay).

In an MLP, we could use subgraph_grad to iteratively backpropagate:

x, t = theano.tensor.fvector('x'), theano.tensor.fvector('t')
w1 = theano.shared(np.random.randn(3,4))
w2 = theano.shared(np.random.randn(4,2))
a1 = theano.tensor.tanh(theano.tensor.dot(x,w1))
a2 = theano.tensor.tanh(theano.tensor.dot(a1,w2))
cost2 = theano.tensor.sqr(a2 - t).sum()
cost2 += theano.tensor.sqr(w2.sum())
cost1 = theano.tensor.sqr(w1.sum())

params = [[w2],[w1]]
costs = [cost2,cost1]
grad_ends = [[a1], [x]]

next_grad = None
param_grads = []
for i in xrange(2):
    param_grad, next_grad = theano.subgraph_grad(
        wrt=params[i], end=grad_ends[i],
        start=next_grad, cost=costs[i]
    )
    next_grad = dict(zip(grad_ends[i], next_grad))
    param_grads.extend(param_grad)
Parameters:
  • wrt (list of variables) – Gradients are computed with respect to wrt.
  • end (list of variables) – Theano variables at which to end gradient descent (they are considered constant in theano.grad). For convenience, the gradients with respect to these variables are also returned.
  • start (dictionary of variables) – If not None, a dictionary mapping variables to their gradients. This is useful when the gradient on some variables are known. These are used to compute the gradients backwards up to the variables in end (they are used as known_grad in theano.grad).
  • cost (Variable scalar (0-dimensional) variable) –

    Additional costs for which to compute the gradients. For example, these could be weight decay, an l1 constraint, MSE, NLL, etc. May optionally be None if start is provided.

    Warning

    If the gradients of cost with respect to any of the start variables is already part of the start dictionary, then it may be counted twice with respect to wrt and end.

  • details (bool) – When True, additionally returns the list of gradients from start and of cost, respectively, with respect to wrt (not end).
Returns:

Returns lists of gradients with respect to wrt and end, respectively.

Return type:

Tuple of 2 or 4 Lists of Variables

New in version 0.7.

theano.gradient.undefined_grad(x)[source]

Consider the gradient of this variable undefined.

This will generate an error message if its gradient is taken.

The expression itself is unaffected, but when its gradient is computed, or the gradient of another expression that this expression is a subexpression of, an error message will be generated specifying such gradient is not defined.

Parameters:x (Variable) – A Theano expression whose gradient should be undefined.
Returns:An expression equivalent to x, with its gradient undefined.
Return type:Variable
theano.gradient.verify_grad(fun, pt, n_tests=2, rng=None, eps=None, out_type=None, abs_tol=None, rel_tol=None, mode=None, cast_to_output_type=False, no_debug_ref=True)[source]

Test a gradient by Finite Difference Method. Raise error on failure.

Raises an Exception if the difference between the analytic gradient and numerical gradient (computed through the Finite Difference Method) of a random projection of the fun’s output to a scalar exceeds the given tolerance.

Examples

>>> verify_grad(theano.tensor.tanh,
...             (np.asarray([[2, 3, 4], [-1, 3.3, 9.9]]),),
...             rng=np.random)
Parameters:
  • fun (a Python function) – fun takes Theano variables as inputs, and returns a Theano variable. For instance, an Op instance with a single output.
  • pt (list of numpy.ndarrays) – Input values, points where the gradient is estimated. These arrays must be either float16, float32, or float64 arrays.
  • n_tests (int) – number of times to run the test
  • rng (numpy.random.RandomState, optional) – random number generator used to sample the output random projection u, we test gradient of sum(u * fun) at pt
  • eps (float, optional) – stepsize used in the Finite Difference Method (Default None is type-dependent). Raising the value of eps can raise or lower the absolute and relative errors of the verification depending on the Op. Raising eps does not lower the verification quality for linear operations. It is better to raise eps than raising abs_tol or rel_tol.
  • out_type (string) – dtype of output, if complex (i.e., ‘complex32’ or ‘complex64’)
  • abs_tol (float) – absolute tolerance used as threshold for gradient comparison
  • rel_tol (float) – relative tolerance used as threshold for gradient comparison
  • cast_to_output_type (bool) – if the output is float32 and cast_to_output_type is True, cast the random projection to float32. Otherwise it is float64. float16 is not handled here.
  • no_debug_ref (bool) – Don’t use DebugMode for the numerical gradient function.

Note

This function does not support multiple outputs. In tests/test_scan.py there is an experimental verify_grad that covers that case as well by using random projections.

theano.gradient.zero_grad(x)[source]

Consider an expression constant when computing gradients.

The expression itself is unaffected, but when its gradient is computed, or the gradient of another expression that this expression is a subexpression of, it will be backpropagated through with a value of zero. In other words, the gradient of the expression is truncated to 0.

Parameters:x (Variable) – A Theano expression whose gradient should be truncated.
Returns:An expression equivalent to x, with its gradient truncated to 0.
Return type:Variable

List of Implemented R op

See the gradient tutorial for the R op documentation.

list of ops that support R-op:
  • with test [Most is tensor/tests/test_rop.py]
    • SpecifyShape
    • MaxAndArgmax
    • Subtensor
    • IncSubtensor set_subtensor too
    • Alloc
    • Dot
    • Elemwise
    • Sum
    • Softmax
    • Shape
    • Join
    • Rebroadcast
    • Reshape
    • Flatten
    • DimShuffle
    • Scan [In scan_module/tests/test_scan.test_rop]
  • without test
    • Split
    • ARange
    • ScalarFromTensor
    • AdvancedSubtensor1
    • AdvancedIncSubtensor1
    • AdvancedIncSubtensor

Partial list of ops without support for R-op:

  • All sparse ops
  • All linear algebra ops.
  • PermuteRowElements
  • Tile
  • AdvancedSubtensor
  • TensorDot
  • Outer
  • Prod
  • MulwithoutZeros
  • ProdWithoutZeros
  • CAReduce(for max,... done for MaxAndArgmax op)
  • MaxAndArgmax(only for matrix on axis 0 or 1)