<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/probability/blob/v0.25.0/tensorflow_probability/python/optimizer/convergence_criteria/convergence_criterion.py#L20-L131) |

Base class for stopping rules.

    tfp.optimizer.convergence_criteria.ConvergenceCriterion(
        min_num_steps=None, name=None
    )

A convergence criterion determines when an optimization has converged given
its history of losses, gradients, and parameter values. Each criterion is
responsible for propagating from step to step whatever state it needs to
represent the relevant aspects of that history (for example, a moving average
of previous loss values or gradients). In particular, subclasses must
implement:

- `_bootstrap(loss, grads, parameters)`: takes the initial loss, gradients, and values of parameters, and returns a (structure of) `Tensor`(s) representing the initial values of any auxiliary quantities tracked by the convergence criterion.
- `_one_step(step, loss, grads, window_size, auxiliary_state)`: At integer `step >= 1`, takes the current loss, gradients, and values of parameters, along with any auxiliary state carried over from the previous step, and returns `(has_converged, updated_auxiliary_state)`, where `has_converged` is a boolean `Tensor`, and `updated_auxiliary_state` is a (structure of) Tensor(s) matching `auxiliary_state`, containing whatever information must be propagated to the next timestep.

<br />

<br />

<br />

| ## Args ||
|---|---|
| `min_num_steps` | optional int `Tensor` minimum number of steps before stopping. If set, subclass return values of `has_converged=True` will be ignored until `step >= min_num_steps`. Default value: `None`. |
| `name` | optional Python `str` name prefixed to ops created by this class. |

<br />

<br />

<br />

<br />

| ## Attributes ||
|---|---|
| `min_num_steps` | <br /> <br /> |
| `name` | <br /> <br /> |

<br />

## Methods

### `bootstrap`

[View source](https://github.com/tensorflow/probability/blob/v0.25.0/tensorflow_probability/python/optimizer/convergence_criteria/convergence_criterion.py#L67-L87)

    bootstrap(
        loss, grads, parameters
    )

Returns a structure of `Tensors` for the rule's state at step 0.

The shape of the `Tensor`s specifying `loss`, `grads`, and `parameters` may
optionally be prefixed by one or more batch dimension(s).

<br />

<br />

<br />

| Args ||
|---|---|
| `loss` | float `Tensor` initial value of loss being optimized. |
| `grads` | list of float `Tensor` gradients of `loss` wrt `parameters`. |
| `parameters` | list of float `Tensor` initial values of parameters being optimized. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| `initial_auxiliary_state` | (Structure of) `Tensor`(s) representing the initial auxiliary state carried forward by this criterion. |

<br />

### `one_step`

[View source](https://github.com/tensorflow/probability/blob/v0.25.0/tensorflow_probability/python/optimizer/convergence_criteria/convergence_criterion.py#L89-L125)

    one_step(
        step, loss, grads, parameters, auxiliary_state
    )

Updates tracked quantities for a new step, and determines if converged.

The shape of the `Tensor`s specifying `loss`, `grads`, and `parameters` may
optionally be prefixed by one or more batch dimension(s). In this case,
the returned value `has_converged` will have shape equal to the broadcast
batch shape of whichever of those quantities is used by this convergence
criterion, and the quantities defining the convergence criterion (
`min_num_steps`, etc.).

<br />

<br />

<br />

| Args ||
|---|---|
| `step` | integer `Tensor` index of the current step, where `step >= 1` (on step `0`, `initial_state` should be called instead). |
| `loss` | float `Tensor` value of loss at the current step. |
| `grads` | list of float `Tensor` gradients of `loss` wrt `parameters`. |
| `parameters` | list of float `Tensor` current values of parameters being optimized. |
| `auxiliary_state` | the (structure of) `Tensor`(s) containing state carried forward from the previous step. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| `has_converged` | boolean `Tensor` indicating whether the optimization has converged. |
| `updated_auxiliary_state` | (Structure of) `Tensor`(s) representing updated quantities tracked by the convergence criterion. This should match the structure of the value returned by `bootstrap`. |

<br />