Showing cs.LGShow all
3 papers · 1 filter
cs.LG2025
Cross-Entropy Is All You Need To Invert the Data Generating Process
Patrik Reizinger, Alice Bizeul, Attila Juhos +4
Supervised learning has become a cornerstone of modern machine learning, yet a comprehensive theory explaining its effectiveness remains elusive. Empirical phenomena, such as neura…
cs.LG2025
From Pixels to Components: Eigenvector Masking for Visual Representation Learning
Alice Bizeul, Thomas Sutter, Alain Ryser +3
Predicting masked from visible parts of an image is a powerful self-supervised approach for visual representation learning. However, the common practice of masking random patches o…
cs.LG2024
A Probabilistic Model Behind Self-Supervised Learning
Alice Bizeul, Bernhard Schölkopf, Carl Allen
In self-supervised learning (SSL), representations are learned via an auxiliary task without annotated labels. A common task is to classify augmentations or different modalities of…