Pith. sign in

REVIEW 1 cited by

A Geometric Perspective on Autoencoders

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 2309.08247 v2 pith:RZLMXFOY submitted 2023-09-15 cs.LG cs.AIcs.CG

classification cs.LGcs.AIcs.CG
keywords geometricmanifoldautoencoderautoencoderschartcoordinatedatagiven
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

This paper presents the geometric aspect of the autoencoder framework, which, despite its importance, has been relatively less recognized. Given a set of high-dimensional data points that approximately lie on some lower-dimensional manifold, an autoencoder learns the \textit{manifold} and its \textit{coordinate chart}, simultaneously. This geometric perspective naturally raises inquiries like "Does a finite set of data points correspond to a single manifold?" or "Is there only one coordinate chart that can represent the manifold?". The responses to these questions are negative, implying that there are multiple solution autoencoders given a dataset. Consequently, they sometimes produce incorrect manifolds with severely distorted latent space representations. In this paper, we introduce recent geometric approaches that address these issues.

Discussion (0). Sign in 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. From Points to Spheres: A Geometric Reinterpretation of Variational Autoencoders

    cs.LG 2025-07 conditional novelty 4.0 of 10

    The paper claims that KL-induced compactness, not stochasticity, is the key to VAE generative capability, supported by new latent-space uniformity metrics and codebook regularizer experiments.

Pith tools