Trading robust representations for sample complexity through self-supervised visual experience.
Andrea TacchettiStephen VoineaGeorgios EvangelopoulosPublished in: NeurIPS (2018)
Keyphrases
- sample complexity
- pac learning
- theoretical analysis
- learning problems
- supervised learning
- vc dimension
- upper bound
- learning algorithm
- special case
- irrelevant features
- lower bound
- training examples
- generalization error
- sample size
- linear threshold
- pac model
- active learning
- reinforcement learning
- machine learning
- state space
- training data
- covering numbers
- pac learnability
- number of irrelevant features