Questions tagged [pytorch-distributions]
6 questions
3
votes
2 answers
KL Divergence of two torch.distribution.Distribution objects
I'm trying to determine how to compute KL Divergence of two torch.distribution.Distribution objects. I couldn't find a function to do that so far. Here is what I've tried:
import torch as t
from torch import distributions as tdist
import…
ikamen
- 3,175
- 1
- 25
- 47
0
votes
0 answers
RuntimeError: RPC has not been initialized. Call torch.distributed.rpc.init_rpc first
I am making the experimental FedAvg simulation using the Pytorch RPC, but the server side throws errors when I run it. It seems that it is my coding problem, but I don't know what the problem is. Here are some related code snippets:
.
.
.
#Start…
Evan Christan123
- 1
- 1
0
votes
1 answer
Can we use torch.multiprocessing.spawn with wandb sweep hyper-parameter tuning?
Can we use torch.multiprocessing.spawn with wandb.sweep (https://docs.wandb.ai/guides/sweeps).
torch.multiprocessing.spawn(func, nprocs=world_size, join=True)
I tried but got errors and cannot find tutorials.
skytree
- 1,060
- 2
- 13
- 38
0
votes
0 answers
How to make torch.distributions.MultivariateNormal accept zero values on the diagonal of covariance matrix?
I use torch.normal to generate (1,n)-dimensional samples with an std vector that includes zero values. This doesn't generate any errors (when std[k] is zero the corresponding mean[k] is sampled).
However, torch.distributions.MultivariateNormal…
Rima
- 3
- 2
0
votes
0 answers
Multi Dimensional Sample from a given distribution
I'm trying to genrate a binary sample with multiple dimensions of which i can control the probability distribution as well, i found it useful with torch.distributions.binomial which allows controlling the probability distribution but dosen't help…
Ctrl7
- 161
- 2
- 12
0
votes
1 answer
Learning multivariate normal covariance matrix using pytorch
I am trying to learn a multivariate normal covariance matrix (Sigma, ∑) using some observations.
The way I went at it is by using pytorch.distributions.MultivariateNormal:
import torch
from torch.distributions import MultivariateNormal
# I tried…
EyalItskovits
- 116
- 1
- 9