On minimal variations for unsupervised representation learning

Vivien Cabannes, Alberto Bietti, Randall Balestriero

Submitted on 7 November 2022


Unsupervised representation learning aims at describing raw data efficiently to solve various downstream tasks. It has been approached with many techniques, such as manifold learning, diffusion maps, or more recently self-supervised learning. Those techniques are arguably all based on the underlying assumption that target functions, associated with future downstream tasks, have low variations in densely populated regions of the input space. Unveiling minimal variations as a guiding principle behind unsupervised representation learning paves the way to better practical guidelines for self-supervised learning algorithms.


Comment: 5 pages, 1 figure; 1 table

Subjects: Computer Science - Machine Learning; Computer Science - Artificial Intelligence; Statistics - Machine Learning; 68Q32; G.3