View source on GitHub
|
Use Gauss-Hermite quadrature to form quadrature on positive-reals.
tfp.distributions.quadrature_scheme_lognormal_gauss_hermite(
loc, scale, quadrature_size, validate_args=False, name=None
)
tfp.distributions.quadrature_scheme_lognormal_gauss_hermite
Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.
Last updated 2023-11-21 UTC.
[null,null,["Last updated 2023-11-21 UTC."],[],[],null,["# tfp.distributions.quadrature_scheme_lognormal_gauss_hermite\n\n\u003cbr /\u003e\n\n|----------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/tensorflow/probability/blob/v0.23.0/tensorflow_probability/python/distributions/poisson_lognormal.py#L44-L84) |\n\nUse Gauss-Hermite quadrature to form quadrature on positive-reals. \n\n tfp.distributions.quadrature_scheme_lognormal_gauss_hermite(\n loc, scale, quadrature_size, validate_args=False, name=None\n )\n\n| **Note:** for a given `quadrature_size`, this method is generally less accurate than `quadrature_scheme_lognormal_quantiles`.\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|-------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| `loc` | `float`-like (batch of) scalar `Tensor`; the location parameter of the LogNormal prior. |\n| `scale` | `float`-like (batch of) scalar `Tensor`; the scale parameter of the LogNormal prior. |\n| `quadrature_size` | Python `int` scalar representing the number of quadrature points. |\n| `validate_args` | Python `bool`, default `False`. When `True` distribution parameters are checked for validity despite possibly degrading runtime performance. When `False` invalid inputs may silently render incorrect outputs. |\n| `name` | Python `str` name prefixed to Ops created by this class. |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ------- ||\n|---------|-------------------------------------------------------------------------------------------------------|\n| `grid` | (Batch of) length-`quadrature_size` vectors representing the `log_rate` parameters of a `Poisson`. |\n| `probs` | (Batch of) length-`quadrature_size` vectors representing the weight associate with each `grid` value. |\n\n\u003cbr /\u003e"]]