The paper investigates how autoencoder parameters reflect the statistical properties of their training data. By analyzing the spectral characteristics of the parameter matrices, the authors show that singular values correspond to the eigenvalues of the data covariance matrix, linking data and parameter spaces. Experiments on CIFAR‑10 and FashionMNIST demonstrate that these spectral vectors can accurately differentiate models trained on different data subsets without complex generation methods or access to the original samples.
By Maria Nikitina, Anton Bishuk, Oleg Bakhteev
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.
By Vicente Conde Mendes, Lorenzo Bardone, C\'edric Koller, Jorge Medina Moreira, Vittorio Erba, Emanuele Troiani, Lenka Zdeborov\'a
arXiv:2606. 25900v1 Announce Type: new Abstract: Variational Autoencoders (VAEs) belong to a family of autoencoders with probabilistic properties, making them well suited for generating data by producing a smooth and continuous latent space.
By Gananath R
arXiv:2608.29867v1 Announce Type: new
Abstract: Autoencoders are widely used for nonlinear dimensionality reduction and manifold learning. While most common implementations rely on both nonlinear enc...
By Louen Pottier, Louis Lesueur, Anders Thorin
Variational Autoencoders (VAEs) belong to a family of autoencoders with probabilistic properties, making them well suited for generating data by producing a smooth and continuous latent space. Despite being introduced over a decade ago, the method continues to be widely adopted in both research and industry for diverse applications.
arXiv:2609.28409v1 Announce Type: cross
Abstract: Vector Symbolic Algebras project data structures into a hyperdimensional vector space through the application of their vector algebras to randomly ge...
By Mohamed Malek Abid, P. Michael Furlong