Pith. sign in

REVIEW 1 cited by

Variational autoencoders in the presence of low-dimensional data: landscape and implicit bias

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 2112.06868 v2 pith:PYKFZVMK submitted 2021-12-13 cs.LG stat.ML

classification cs.LGstat.ML
keywords trainingmanifoldconjecturedatagroundtruthautoencodersbias
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Variational Autoencoders are one of the most commonly used generative models, particularly for image data. A prominent difficulty in training VAEs is data that is supported on a lower-dimensional manifold. Recent work by Dai and Wipf (2020) proposes a two-stage training algorithm for VAEs, based on a conjecture that in standard VAE training the generator will converge to a solution with 0 variance which is correctly supported on the ground truth manifold. They gave partial support for that conjecture by showing that some optima of the VAE loss do satisfy this property, but did not analyze the training dynamics. In this paper, we show that for linear encoders/decoders, the conjecture is true-that is the VAE training does recover a generator with support equal to the ground truth manifold-and does so due to an implicit bias of gradient descent rather than merely the VAE loss itself. In the nonlinear case, we show that VAE training frequently learns a higher-dimensional manifold which is a superset of the ground truth manifold.

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. Characterizing Neural Manifolds' Properties and Curvatures using Normalizing Flows

    q-bio.NC 2025-06 conditional novelty 6.0 of 10

    A normalizing flow with a mixture-of-Gaussians latent space and a quadratic post-hoc approximation yields higher-order correlations and curvature estimates for neural manifolds in macaque visual cortex.

Pith tools