Pyro Discussion Forum
Aug 18, 2025 · Forum For Pyro Developers
Bad performance Bayesian Convolutional Neural Network - Misc.
Apr 28, 2025 · Hello Pyro community, I’m trying to build a Bayesian CNN for MNIST classification using Pyro, but despite seeing the ELBO loss decrease to around 10 during training, the …
Learning rate scheduling in numpyro - Pyro Discussion Forum
Sep 18, 2023 · pyro provides access to the pytorch schedulers, and the pyro ClippedAdam also has a specific learning rate decay parameter. I can not find anything of the sort in numpyro, …
Simple Bayesian Network Example? - Pyro Discussion Forum
Jul 6, 2022 · I cannot differentiate the usages between pyro.sample and pyro.param. Could you please give an example of simple discrete bayesian network where each node is categorical …
Reducing MCMC memory usage - numpyro - Pyro Discussion Forum
Oct 15, 2023 · I am running NUTS/MCMC (on multiple CPU cores) for a quite large dataset (400k samples) for 4 chains x 2000 steps. mcmc.run actually ran until the end, but then died with an …
Implementation & normalizing flow in matrix normal distribution
Nov 1, 2024 · Hi, I’m working on a model where the likelihood follows a matrix normal distribution, X ~ MN_{n,p} (M, U, V). I’m using conjugate priors: M ~ MN U ~ Inverse Wishart V ~ Inverse …
How to reduce the memory usage? - numpyro - Pyro Discussion …
Jan 15, 2025 · Hello, I’m having a “Memory Exhausion” issue: Is there a way to reduce the usage of memory of the algorithm? (Some sort of batch_size?) Thanks in advance
Moving MCMC from CPU to GPU - Pyro Discussion Forum
May 9, 2022 · Hi all, I’ve read a few posts on the forum about how to use GPU for MCMC: Transfer SVI, NUTS and MCMC to GPU (Cuda), How to move MCMC run on GPU to CPU …
GPU available but slow compared to CPU on BNN example
Nov 25, 2021 · Well, It is a VI + NeuraReparametrisation to perform a NUTS. Currently, we have found that the job runs 100% on CPU while GPU memory is activated. it’s as if the CPU was …
Multi GPU num_samples - Pyro Discussion Forum
Jan 10, 2021 · Hello I was wondering if it’s possible to parallelize the number of particles used to estimate the ELBO over multiple GPUs (i.e. num_particles=40, and if we have 4 GPUs, then …