PAC-Bayes Compression Bounds So Tight That They Can Explain Generalization.
Sanae LotfiMarc FinziSanyam KapoorAndres PotapczynskiMicah GoldblumAndrew Gordon WilsonPublished in: CoRR (2022)
Keyphrases
- pac bayes
- generalization bounds
- risk bounds
- linear classifiers
- data dependent
- upper bound
- lower bound
- data compression
- learning theory
- generalization ability
- vc dimension
- compression scheme
- image compression
- worst case
- statistical learning theory
- compression algorithm
- model selection
- compression ratio
- ranking algorithm
- learning algorithm
- large deviations