Private PAC learning implies finite Littlestone dimension.
Noga AlonRoi LivniMaryanthe MalliarisShay MoranPublished in: STOC (2019)
Keyphrases
- pac learning
- concept classes
- mistake bound
- sample complexity
- uniform distribution
- computational learning theory
- learning theory
- sample size
- learning problems
- vc dimension
- decision lists
- concept class
- pac model
- theoretical analysis
- target concept
- membership queries
- generalization error
- upper bound
- special case
- active learning
- linear threshold
- learning algorithm
- target function
- training examples
- agnostic learning
- efficiently learnable
- boolean functions
- training data