Hi, I wanted to try replacing ADVI with SVGD in my model, but there seems to be no easy way to track its convergence. I suppose I would have to look at the gradient corresponding to each particle (?) - but how do I extract this information in a callback passed to the fit function?

Tracking SVGD convergence

junpenglao February 2, 2020, 12:45pm 2

Topic		Replies	Views
Why SVGD does not display average loss or any metric during the fitting? Questions	0	317	June 2, 2020
Advice on checking convergence with SVGD Questions	0	435	August 21, 2019
SVGD convergence	0	97	June 6, 2024
The current approximation of RV "x" is Nan Questions	3	1926	March 19, 2019
Make predictions with the particles of SVGD Questions	6	1772	November 5, 2018