Neural Information Processing Systems http://nips.cc/

The problem is challenging because the loss distribution and threshold value of each arm are unknown. We study this novel setting by establishing its'equivalence' to Multiple-Play Multi-Armed Bandits (MP-MAB) andCombinatorial Semi-Bandits.

However,givenlimited data, classical GANs have struggled, and strategies like output-regularization, data-augmentation, use of pre-trained models and pruning have been shown to lead to improvements. Notably, the applicability of these strategies is 1) often constrained to particular settings, e.g., availability of a pretrained GAN; or 2) increases training time, e.g., when using pruning.

This work focuses on the active learning in video captioning.

Ontheother extreme, without long-term consistency, generated videos may morph unrealistically betweendifferentscenes.

However, they bring their own set of challenges.