Add bayes-hdc to Libraries#144
Open
rlogger wants to merge 1 commit into
Open
Conversation
bayes-hdc is a JAX-native library for hyperdimensional computing (HDC) and vector symbolic architectures (VSA) with a probabilistic layer (PVSA): Gaussian and Dirichlet hypervector types with closed-form moment propagation, end-to-end variational codebook training via reparameterisation gradients, split-conformal prediction sets with finite-sample coverage guarantees, and group-theoretic equivariance verifiers. Eight classical VSA models (BSC, MAP, HRR, FHRR, BSBC, CGR, MCR, VTB) under a uniform pytree-native API. 506 unit tests, 93% line coverage, MIT license.
Author
|
Update since filing: bayes-hdc is now on PyPI ( |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What this PR adds
Adds
bayes-hdcto the Libraries section, immediately after Dynamax (positioned with the probabilistic / uncertainty-quantification cluster — NumPyro, Fortuna, BlackJAX, Dynamax — which is the closest topical fit).What
bayes-hdcisA JAX-native library for hyperdimensional computing (HDC) and vector symbolic architectures (VSA) with a built-in probabilistic layer (PVSA):
GaussianHVandDirichletHVdistributional hypervector types with closed-form moment propagation underbind,bundle,permute, andcleanup.lax.scan-compiled Adam loop.Z/d.To my knowledge no other open-source HDC library offers a JAX backend, end-to-end gradient training, or formal coverage guarantees — TorchHD covers PyTorch, hdlib targets bioinformatics on NumPy, NengoSPA is biologically-realistic spiking VSA.
bayes-hdcfills the JAX / probabilistic / UQ lane.Quality signals
-W(warnings as errors).ruff check,ruff format --check,mypy bayes_hdc/all clean.pmapandshard_mapwrappers degrade gracefully on single-device hosts.docs/audit/.Awesome-list checklist
- [Name](url) - Description. <stars badge>).jit/vmap/grad/pmap/shard_map).Thanks for maintaining this list — it was useful when I was scoping the project.