-
I read the paper carefully, the formula in paper is fundamentally wrong.
- Under the formula (2) and (3), the probility output has a gaussian distribution. However, the probility can't be a gaussia…
-
This page will have the suggested 12 packages to talk about and resources related to these projects.
This should be in a markdown file.
-
We're not planning to build the simulator for a while but I wanted to start this feature request so we can keep notes about the simulator.
Some specific feature ideas:
- Test the effect of:
- chang…
-
## Note
This might be my first pytorch issue.
## 🐛 Bug
torch.distributions.kl_divergence seems numerically unsafe for Bernoullis. In the following script, I compare with a hand-written diverg…
-
We need to establish a method for systematicly testing randomize() function validity.
**Method proposal**
The randomize() function implemented in Braph and BCT are considered to be "ground trut…
-
An LDA model's `components_` isn't easily interpretable:
``` py
>>> X = np.abs(np.random.RandomState(42).randn(5, 4))
>>> from sklearn.decomposition import LatentDirichletAllocation
>>> lda = LatentD…
-
### Description
Sorry to bother you. I am wondering how much, if any, of this paper https://ssg.lancs.ac.uk/wp-content/uploads/ndss_preprint.pdf is implememented in this crate?
Much of the paper s…
-
Hi! I have several questions/requests regarding value learning https://github.com/deepmind/rlax/blob/master/rlax/_src/value_learning.py
1. If I want to use the `_quantile_regression_loss` without …
-
## Experiment Repository Creation Request for Probability and Statistics Lab - IITD
Use this to get your experiment repository created or updated on GitHub under Virtual Labs organization.
1. ####…
-
In my current research, I need to use the gradient of the log-density, also known as [score function](https://en.wikipedia.org/wiki/Score_(statistics)). Sure, I can compute it with AD, but in many cas…