I think GFlowNets can help with sequential updating without the limitations of variational inference (which is, I guess, what @ricardoV94 meant by the phrase “textbooks always work with simple conjugate prior models”): see section 4. in Notion – The all-in-one workspace for your notes, tasks, wikis, and databases.. This is what I suggested to implement in Sampling with a diffusion model
Related Topics
Topic | Replies | Views | Activity | |
---|---|---|---|---|
Incremental updates with independent multi-dimensional parameters | 0 | 442 | October 12, 2020 | |
Prior based on sample | 2 | 494 | December 13, 2021 | |
Deploying Bayesian Models with PyMC3 | 2 | 1235 | May 23, 2020 | |
Minibatch and NUTS | 11 | 3154 | June 22, 2018 | |
Posterior Predictive Sampling in PyMC3 by Luciano Paz | 2 | 1567 | June 6, 2024 |