Intrinsic dimensionality and generalization properties of the R-norm inductive bias.
Navid ArdeshirDaniel J. HsuClayton Hendrick SanfordPublished in: COLT (2023)
Keyphrases
- intrinsic dimensionality
- inductive bias
- inductive learning
- machine learning
- pac learning
- noisy data
- vector space
- prior knowledge
- dimensionality reduction
- supervised learning
- hypothesis space
- domain knowledge
- training examples
- multitask learning
- domain theory
- training set
- probability density
- learning algorithm
- objective function
- uniform distribution
- training data
- previously learned
- sample selection
- high dimensional
- sample complexity
- feature selection
- computer vision
- active learning