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
Signed reviews
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.
Forward citations
Cited by 3 Pith papers
-
NAE: Normalizing AutoEncoder
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...
-
Geometry-Preserving Encoder/Decoder in Latent Generative Models
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.
-
Expressive Score-Based Priors for Distribution Matching with Geometry-Preserving Regularization
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.
Discussion (0). Continue with ORCID to comment.