A Labelled Sample Compression Scheme of Size at Most Quadratic in the VC Dimension.
Farnam MansouriSandra ZillesPublished in: CoRR (2022)
Keyphrases
- compression scheme
- vc dimension
- image compression
- sample size
- data compression
- covering numbers
- compression ratio
- compression algorithm
- vapnik chervonenkis dimension
- statistical learning theory
- distribution free
- concept classes
- generalization bounds
- pac learning
- upper bound
- concept class
- pairwise
- lower bound
- sample complexity
- image quality
- computational complexity
- learning algorithm
- function classes
- linear functions
- objective function
- learning process
- active learning