-
We have recently encountered a strange bug which manifested itself in `nan` values resulting from the computation - specifically in the gradient computation - under specific circumstances which I'll t…
lumip updated
2 years ago
-
- News
- [Facebook has gone~ Meta has come!!!!](https://news.naver.com/main/read.naver?mode=LSD&mid=sec&sid1=101&oid=015&aid=0004622175)
- [State of AI Report 2021](https://www.stateof.ai/)
![…
-
We also might want to have backends be able to influence the default thinning (e.g. for ADVI/optimizing fits it makes no sense to thin as the samples from the approximate posterior are already indepen…
-
Dear Misha Laskin,
I am very grateful for open-sourcing the well-written code.
It is really helpful for my research!
However, I have one question about the implementation of fine-tuning APS.
…
-
Hi,
I am working with this for quite some time to replicate onto my own thesis, but I am having some troubles understanding how the Jacobian is calculated.
Can someone share some insight? Or po…
-
Where can I view the paper "Bayesian Confidence Calibration for Epistemic Uncertainty Modelling"?
I can't find it anywhere on the internet including on google scholar search. I can only find is the …
-
Hi,
Thanks for sharing your code. I am adapting your code on my own dataset with different pre-processing and I faced the following issue:
As mentioned in "_chunk" function of realnvp.py you hav…
-
Most of the ML based probabilistic packages (Pyro--> torch, Tensorflow Probability --> tensorflow) have the prerequisite that everything is differentiable. If our forward solver doesnt pass jacobians …
-
This is a meta-issue for information/discussion about [my GSoC project](https://summerofcode.withgoogle.com/projects/#6482838431465472)
The original plan (as in [the proposal](https://www.overleaf.…
-
**Is your feature request related to a problem? Please describe.**
From a trained scVI model one can get the variable `\rho` (mean of the Gamma in the GammaPoisson) very easily with
`model.get_norma…