VC dimension of partially quantized neural networks in the overparametrized regime.
Yutong WangClayton D. ScottPublished in: CoRR (2021)
Keyphrases
- vc dimension
- neural network
- upper bound
- sample complexity
- lower bound
- concept classes
- sample size
- inductive inference
- vapnik chervonenkis dimension
- statistical learning theory
- empirical risk minimization
- covering numbers
- generalization bounds
- distribution free
- pac learnability
- pac learning
- concept class
- back propagation
- worst case
- np hard
- uniform convergence
- euclidean space
- compression scheme
- data sets
- active learning
- artificial neural networks
- learning problems
- theoretical analysis