Narrowing confidence interval width of PAC learning risk function by algorithmic inference.
Bruno ApolloniDario MalchiodiPublished in: AI&M (2002)
Keyphrases
- pac learning
- confidence intervals
- sample size
- uniform distribution
- sample complexity
- model selection
- learning theory
- vc dimension
- upper bound
- learning problems
- pac model
- data sets
- concept classes
- markov chain
- loss function
- boolean functions
- theoretical analysis
- supervised learning
- small number
- np hard
- learning algorithm
- statistical queries
- data mining