ICML

Demonstrates the benefit of curriculum learning with different scoring and pacing functions on various small datasets.

SimCLR, a simple unsupervised contrastive learning framework, uses data augmentation for positive pairs, a nonlinear projection head, normalized temperature-scaled cross entropy loss, and large batch sizes to achieve SotA in self-supervised, semi-supervised, and transfer learning domains.

A large scale, comprehensive study challenges various assumptions in learning disentangled representations, which motivates demonstrating concrete benefits in robust experimental setups in future work.

Investigates automatically generating curricula based on a variety of progress signals that are computed for each data sample.

Applies curriculum learning to a RL context to achieve policies.