<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/__init__.py) |

TensorFlow Probability Optimizer python package.

## Modules

[`convergence_criteria`](https://www.tensorflow.org/probability/api_docs/python/tfp/optimizer/convergence_criteria) module: TensorFlow Probability convergence criteria for optimizations.

[`linesearch`](https://www.tensorflow.org/probability/api_docs/python/tfp/optimizer/linesearch) module: Line-search optimizers package.

## Classes

[`class StochasticGradientLangevinDynamics`](https://www.tensorflow.org/probability/api_docs/python/tfp/optimizer/StochasticGradientLangevinDynamics): An optimizer module for stochastic gradient Langevin dynamics.

[`class VariationalSGD`](https://www.tensorflow.org/probability/api_docs/python/tfp/optimizer/VariationalSGD): An optimizer module for constant stochastic gradient descent.

## Functions

[`bfgs_minimize(...)`](https://www.tensorflow.org/probability/api_docs/python/tfp/optimizer/bfgs_minimize): Applies the BFGS algorithm to minimize a differentiable function.

[`converged_all(...)`](https://www.tensorflow.org/probability/api_docs/python/tfp/optimizer/converged_all): Condition to stop when all batch members have converged or failed.

[`converged_any(...)`](https://www.tensorflow.org/probability/api_docs/python/tfp/optimizer/converged_any): Condition to stop when any batch member converges, or all have failed.

[`differential_evolution_minimize(...)`](https://www.tensorflow.org/probability/api_docs/python/tfp/optimizer/differential_evolution_minimize): Applies the Differential evolution algorithm to minimize a function.

[`differential_evolution_one_step(...)`](https://www.tensorflow.org/probability/api_docs/python/tfp/optimizer/differential_evolution_one_step): Performs one step of the differential evolution algorithm.

[`lbfgs_minimize(...)`](https://www.tensorflow.org/probability/api_docs/python/tfp/optimizer/lbfgs_minimize): Applies the L-BFGS algorithm to minimize a differentiable function.

[`nelder_mead_minimize(...)`](https://www.tensorflow.org/probability/api_docs/python/tfp/optimizer/nelder_mead_minimize): Minimum of the objective function using the Nelder Mead simplex algorithm.

[`nelder_mead_one_step(...)`](https://www.tensorflow.org/probability/api_docs/python/tfp/optimizer/nelder_mead_one_step): A single iteration of the Nelder Mead algorithm.

[`proximal_hessian_sparse_minimize(...)`](https://www.tensorflow.org/probability/api_docs/python/tfp/optimizer/proximal_hessian_sparse_minimize): Minimize using Hessian-informed proximal gradient descent.

[`proximal_hessian_sparse_one_step(...)`](https://www.tensorflow.org/probability/api_docs/python/tfp/optimizer/proximal_hessian_sparse_one_step): One step of (the outer loop of) the minimization algorithm.