Pith. sign in

REVIEW 1 cited by

Variational Hyper-Encoding Networks

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2005.08482 v2 pith:7XA2EQDO submitted 2020-05-18 stat.ML cs.LG

classification stat.MLcs.LG
keywords distributionhypervaethetaparametersdistributionsencodegaussiangenerate
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We propose a framework called HyperVAE for encoding distributions of distributions. When a target distribution is modeled by a VAE, its neural network parameters \theta is drawn from a distribution p(\theta) which is modeled by a hyper-level VAE. We propose a variational inference using Gaussian mixture models to implicitly encode the parameters \theta into a low dimensional Gaussian distribution. Given a target distribution, we predict the posterior distribution of the latent code, then use a matrix-network decoder to generate a posterior distribution q(\theta). HyperVAE can encode the parameters \theta in full in contrast to common hyper-networks practices, which generate only the scale and bias vectors as target-network parameters. Thus HyperVAE preserves much more information about the model for each task in the latent space. We discuss HyperVAE using the minimum description length (MDL) principle and show that it helps HyperVAE to generalize. We evaluate HyperVAE in density estimation tasks, outlier detection and discovery of novel design classes, demonstrating its efficacy.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Temporal Variational Implicit Neural Representations

    cs.LG 2025-06 conditional novelty 6.0 of 10

    TV-INRs is a variational implicit neural representation model for irregular multivariate time series that performs imputation and forecasting with a single forward pass.

Pith tools