arXiv:2502. 03227v2 Announce Type: replace Abstract: Minimally redundant representations are typically learned by minimizing feature covariance.
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.
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.
arXiv:2509. 01235v2 Announce Type: replace Abstract: Balancing training accuracy and adversarial robustness has beeen a challenge since the birth of deep learning.
arXiv:2510. 11709v2 Announce Type: replace-cross Abstract: Why do adversarial examples exist, and why do they transfer between models?
arXiv:2606. 01746v1 Announce Type: cross Abstract: Modern neural networks are highly susceptible to adversarial perturbations.
arXiv:2412. 08394v2 Announce Type: replace Abstract: Deep neural networks (DNNs) are vulnerable to adversarial samples crafted by adding imperceptible perturbations to clean data, potentially leading to incorrect and dangerous predictions.
arXiv:2504. 18455v2 Announce Type: replace-cross Abstract: We study distributed multiview representation learning, a problem in which $K$ clients each observe a distinct but possibly statistically correlated view.
arXiv:2607. 05653v1 Announce Type: new Abstract: Principal Component Analysis or PCA-like properties (orthogonality, variance ranking) are seldom realized in deep autoencoder architectures.
arXiv:2511. 13749v2 Announce Type: replace Abstract: Deep neural networks are known to be vulnerable to adversarial perturbations, which are small, carefully crafted inputs that lead to incorrect predictions.
arXiv:2606. 26207v1 Announce Type: cross Abstract: Several theoretical works have tried to explain the adversarial vulnerability of deep neural networks through properties of high-dimensional geometry.
arXiv:2601. 19179v2 Announce Type: replace Abstract: Autoencoders have long been considered a nonlinear extension of Principal Component Analysis (PCA).
arXiv:2311. 02960v5 Announce Type: replace Abstract: Over the past decade, deep learning has proven to be a highly effective tool for learning meaningful features from raw data.