Improved Inapproximability of VC Dimension and Littlestone's Dimension via (Unbalanced) Biclique.
Pasin ManurangsiPublished in: ITCS (2023)
Keyphrases
- vc dimension
- concept classes
- vapnik chervonenkis
- sample complexity
- vapnik chervonenkis dimension
- upper bound
- concept class
- sample size
- lower bound
- covering numbers
- statistical learning theory
- generalization bounds
- pac learning
- theoretical analysis
- learning theory
- inductive inference
- decision lists
- efficient learning
- special case
- mistake bound
- learning algorithm
- generalization error
- compression scheme
- worst case
- supervised learning
- learning problems
- pac model
- euclidean space
- function classes
- target concept
- semi supervised
- learning models