-
I was about to start writing code, but I think it's worth having a discussion first. If we're going to realize my eventual vision of autonomous creation of valid "directed graphs of transformations",…
-
Hi guys,
Working on Julia 1.2, Zygote 0.3.4.
I would like to evaluate several distributions in a summary function and get the gradients of it. Doing this in Flux.Tracker is fine, but I somehow …
-
There are a lot of old `unsafe` blocks in Criterion.rs' internals. Many of them were written to work around compiler bugs or missing features that have since been fixed (see https://github.com/japaric…
-
IMHO, `pdf!` and `logpdf!` come in very handy when repeatedly calculating multiple pdf values (re-use of output array, avoiding frequent memory allocation). I think they should be exported.
-
# Overview
Since a distributions has to be re-implemented here and the focus is on AD, I was wondering if it would be of any interested to add reparameterization to `Distribution`. In AD-context you …
-
Dear developers,
Recently, I am trying to write code for calculating MLE via TFP.
I found that TFP will not track the `loc` parameter of multivariate normal when using `GradientTape`
Here is an e…
-
tfp.sts.Autoregressive provides AR modeling. Does tfp.sts have a class or function that provides MA or ARMA modeling?
-
I'm using `chaospy` version 4.3.4 installed with `pip`, on Python 3.8.12
I can't calculate the Expected value with the function `cp.E()`, as it throws the error `UnsupportedFeature`.
Here's the in…
-
Do you support the "heckprobit"(probit with sample selection) model?
Stata supports this model. Does statsmodels supporst this model?
Looking forward to your reply, thank you very much!
-
(semi-random ideas, while thinking about robust or quantile regression)
objective:
find inlier `exog` observations so we can identify outliers that are possibly influential observations. If we downwe…