arXiv Machine Learning August 11, 2026 By Vicente Conde Mendes, Lorenzo Bardone, C\'edric Koller, Jorge Medina Moreira, Vittorio Erba, Emanuele Troiani, Lenka Zdeborov\'a

A solvable high-dimensional model where nonlinear autoencoders learn structure invisible to PCA while test loss misaligns with generalization

Read the original on arXiv Machine Learning →

arXiv:2602. 10680v2 Announce Type: replace-cross Abstract: Many real-world datasets contain hidden structure that cannot be detected by simple linear correlations between input features.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Aug 10

PCAE: Learning Ordered Representations in Latent Space for Intrinsic Dimension Estimation via Principal Component Autoencoder

arXiv:2601. 19179v2 Announce Type: replace Abstract: Autoencoders have long been considered a nonlinear extension of Principal Component Analysis (PCA).

By Qipeng Zhan, Zhuoping Zhou, Zexuan Wang, Li Shen

diffusion

arXiv Machine Learning

Jun 19

Adversarial Dependence Minimization

arXiv:2502. 03227v2 Announce Type: replace Abstract: Minimally redundant representations are typically learned by minimizing feature covariance.

By Pierre-Fran\c{c}ois De Plaen, Tinne Tuytelaars, Marc Proesmans, Luc Van Gool

computer-vision safety

arXiv AI

Jun 30

Perspectives on Latent Factor Indeterminacy and its Implications for Data Representation

arXiv:2606. 28854v1 Announce Type: cross Abstract: The common factor analytic model is related to Helmholtz and Boltzmann machines, can be conceived as a linear autoencoder, or can be thought of as a single-hidden-layer generative neural network.

By Carel F. W. Peeters

arXiv Machine Learning

Jun 2

Discovering Nonlinear Static Relationships in Unlabeled Dataset using Autoencoder with Ordered Variance

arXiv:2402. 14031v2 Announce Type: replace-cross Abstract: This paper presents an autoencoder with ordered variance (AEO), in which the conventional reconstruction loss is augmented by a variance-based regularization term that promotes an ordered structure within the latent space.

By Midhun T. Augustine, Parag Patil, Mani Bhushan, Sharad Bhartiya

diffusion

arXiv Machine Learning

Jul 8

Orthogonal Dendritic Intrinsic Networks: An Architecture for Significance-Ordered, Orthogonal Latent Spaces

arXiv:2607. 05653v1 Announce Type: new Abstract: Principal Component Analysis or PCA-like properties (orthogonality, variance ranking) are seldom realized in deep autoencoder architectures.

By Jeanie Schreiber, Tyrus Berry, Zeeshan Ahmed

arXiv Machine Learning

Jun 3

A Robust Optimization Approach to Sparse Principal Component Analysis

arXiv:2606. 03553v1 Announce Type: cross Abstract: While principal component analysis (PCA) is a fundamental tool for dimensionality reduction, its dense representations make it ill-suited for high-dimensional data.

By David V\"avinggren, Francis Bach, Andr\'e M. H. Teixeira, Dave Zachariah, Ant\^onio H. Ribeiro

diffusion efficiency safety

Related stories

PCAE: Learning Ordered Representations in Latent Space for Intrinsic Dimension Estimation via Principal Component Autoencoder

Adversarial Dependence Minimization

Perspectives on Latent Factor Indeterminacy and its Implications for Data Representation

Discovering Nonlinear Static Relationships in Unlabeled Dataset using Autoencoder with Ordered Variance

Orthogonal Dendritic Intrinsic Networks: An Architecture for Significance-Ordered, Orthogonal Latent Spaces

A Robust Optimization Approach to Sparse Principal Component Analysis