# Black box variational inference with no model derivatives

**URL:** <https://discourse.edwardlib.org/t/black-box-variational-inference-with-no-model-derivatives/1091>\
**Category:** General\
**Created:** [October 1, 2019, 2:50am UTC](https://discourse.edwardlib.org/t/black-box-variational-inference-with-no-model-derivatives/1091 "2019-10-01T02:50:25Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![mukesh\_r](https://avatars.discourse-cdn.com/v4/letter/m/91b2a8/32.png) [@mukesh\_r](https://discourse.edwardlib.org/u/mukesh_r)\
**Post date:** [October 1, 2019, 2:50am UTC](https://discourse.edwardlib.org/t/black-box-variational-inference-with-no-model-derivatives/1091/1 "2019-10-01T02:50:26Z")

</div>

Does Edward have Black Box Variational Inference using Score Gradient?

I have a Finite Element Code as the model, therefore I cannot evaluate the model derivatives (implies, I cannot have likelihood derivatives). So I was looking for the Score Gradient approach for Variational Inference, where I just need to evaluate my likelihood function. In addition, are there any alternatives to perform inference on such models which are implemented in Edward?