Probabilistic Reparameterization Part 2 #2882
Conversation
Summary: Pull Request resolved: pytorch#1532 Add a wrapper for modifying inputs/outputs. This is useful for not only probabilistic reparameterization, but will also simplify other integrated AFs (e.g. MCMC) as well as fixed feature AFs and things like prior-guided AFs Differential Revision: https://internalfb.com/D41629186 fbshipit-source-id: c2d3b339edf44a3167804b095d213b3ba98b5e13
Summary: Creates a new helper method for checking both if a given AF is an instance of a class or if the given AF wraps a base AF that is an instance of a class Differential Revision: D43127722 fbshipit-source-id: 9f5f31b991f15f2b32931f1b9625422c7907495d
Summary: Pull Request resolved: pytorch#1533 Probabilistic reparameterization Differential Revision: D41629217 fbshipit-source-id: a6067c73ce534daf6f6a180fc49720f305827d58
facebook-github-bot
added
the
CLA Signed
|
Currently, the test comparing the Analytic vs MC methods for PR do not give the same (or close to the same) results, which doesn't seem correct to me. I will keep investigating, I imagine it is an issue with my code since the results in the paper seem to be fairly consistent between Analytic and MC (it seems to be that the Analytic approach is giving 0 acqf value everywhere). If anyone does spot any mistakes, please let me know! For reference, the MC method in this test does give similar results to completely enumerating the mixed features. |
|
cc @sdaulton |
|
Great to see you picking this up @TobyBoyne—thanks so much for your contributions to the project! It'll be cool to see PR working with BARK—seems like a natural way to get around using MIP and a good use of those MCMC samples! |
|
Some questions I've found while working on this:
|
Motivation
Probabilistic Reparameterization is a technique for optimizing mixed feature spaces, proposed in [1]. There is an existing pull request (#1533), which requires resolving merge conflicts, and writing tests. This PR continues that work.
[1] Samuel Daulton et al. Bayesian Optimization over Discrete and Mixed Spaces via Probabilistic Reparameterization, NeurIPS '22
Have you read the Contributing Guidelines on pull requests?
Yes
Test Plan
I have currently written tests that optimize the acquisition function. I will also write more fine grained tests: specifically, testing the structure of the chained transforms generated in
factory.py, and testing the new transforms.Related PRs
This continues the work in #1533. The tutorial is in #1534, which also would need updating.