View source on GitHub

Class ExternalOptimizerInterface

Base class for interfaces with external optimization algorithms.

Subclass this and implement _minimize in order to wrap a new optimization algorithm.

ExternalOptimizerInterface should not be instantiated directly; instead use e.g. ScipyOptimizerInterface.


View source


Initialize a new interface instance.


  • loss: A scalar Tensor to be minimized.
  • var_list: Optional list of Variable objects to update to minimize loss. Defaults to the list of variables collected in the graph under the key GraphKeys.TRAINABLE_VARIABLES.
  • equalities: Optional list of equality constraint scalar Tensors to be held equal to zero.
  • inequalities: Optional list of inequality constraint scalar Tensors to be held nonnegative.
  • var_to_bounds: Optional dict where each key is an optimization Variable and each corresponding value is a length-2 tuple of (low, high) bounds. Although enforcing this kind of simple constraint could be accomplished with the inequalities arg, not all optimization algorithms support general inequality constraints, e.g. L-BFGS-B. Both low and high can either be numbers or anything convertible to a NumPy array that can be broadcast to the shape of var (using np.broadcast_to). To indicate that there is no bound, use None (or +/- np.infty). For example, if var is a 2x3 matrix, then any of the following corresponding bounds could be supplied:
    • (0, np.infty): Each element of var held positive.
    • (-np.infty, [1, 2]): First column less than 1, second column less than 2.
    • (-np.infty, [[1], [2], [3]]): First row less than 1, second row less than 2, etc.
    • (-np.infty, [[1, 2, 3], [4, 5, 6]]): Entry var[0, 0] less than 1, var[0, 1] less than 2, etc.
  • **optimizer_kwargs: Other subclass-specific keyword arguments.



View source


Minimize a scalar Tensor.

Variables subject to optimization are updated in-place at the end of optimization.

Note that this method does not just return a minimization Op, unlike Optimizer.minimize(); instead it actually performs minimization by executing commands to control a Session.


  • session: A Session instance.
  • feed_dict: A feed dict to be passed to calls to
  • fetches: A list of Tensors to fetch and supply to loss_callback as positional arguments.
  • step_callback: A function to be called at each optimization step; arguments are the current values of all optimization variables flattened into a single vector.
  • loss_callback: A function to be called every time the loss and gradients are computed, with evaluated fetches supplied as positional arguments.
  • **run_kwargs: kwargs to pass to