Pith. sign in

REVIEW 3 cited by

Isometric 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 2006.09289 v2 pith:2YHR56YT submitted 2020-06-16 cs.LG stat.ML

classification cs.LGstat.ML
keywords datadecoderregularizerdimensionalencoderisometrymanifoldautoencoders
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

High dimensional data is often assumed to be concentrated on or near a low-dimensional manifold. Autoencoders (AE) is a popular technique to learn representations of such data by pushing it through a neural network with a low dimension bottleneck while minimizing a reconstruction error. Using high capacity AE often leads to a large collection of minimizers, many of which represent a low dimensional manifold that fits the data well but generalizes poorly. Two sources of bad generalization are: extrinsic, where the learned manifold possesses extraneous parts that are far from the data; and intrinsic, where the encoder and decoder introduce arbitrary distortion in the low dimensional parameterization. An approach taken to alleviate these issues is to add a regularizer that favors a particular solution; common regularizers promote sparsity, small derivatives, or robustness to noise. In this paper, we advocate an isometry (i.e., local distance preserving) regularizer. Specifically, our regularizer encourages: (i) the decoder to be an isometry; and (ii) the encoder to be the decoder's pseudo-inverse, that is, the encoder extends the inverse of the decoder to the ambient space by orthogonal projection. In a nutshell, (i) and (ii) fix both intrinsic and extrinsic degrees of freedom and provide a non-linear generalization to principal component analysis (PCA). Experimenting with the isometry regularizer on dimensionality reduction tasks produces useful low-dimensional data representations.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

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

  1. NAE: Normalizing AutoEncoder

    cs.LG 2026-08 conditional novelty 6.0 of 10

    A conditional surrogate loss that always picks the gradient estimate aligned with the reconstruction loss improves flow autoencoder training and reaches state-of-the-art generative performance on molecules, tabular da...

  2. Geometry-Preserving Encoder/Decoder in Latent Generative Models

    math.NA 2025-01 conditional novelty 6.0 of 10

    A geometry-preserving encoder/decoder trained by minimizing a logarithmic Gromov-Monge distance converges provably and reconstructs images faster than VAE-based latent generative models.

  3. Expressive Score-Based Priors for Distribution Matching with Geometry-Preserving Regularization

    cs.LG 2025-06 conditional novelty 5.0 of 10

    A likelihood-based distribution matching method uses a score-based prior trained by denoising score matching and a Gromov-Wasserstein semantic-space regularizer, improving fairness, domain adaptation, and domain translation.

Pith tools