Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Loss.

Jeff Z. HaoChen Colin Wei Adrien Gaidon Tengyu Ma

Published in: NeurIPS (2021)

Keyphrases

deep learning
unsupervised learning
machine learning
mental models
approximation guarantees
unsupervised feature learning
restricted boltzmann machine
weakly supervised
deep architectures
decision makers
semi supervised
higher order
multiple images
deep belief networks