Low-weight halfspaces for sparse boolean vectors.
Philip M. LongRocco A. ServedioPublished in: ITCS (2013)
Keyphrases
- high dimension
- sparse data
- boolean functions
- basis vectors
- decision trees
- linear threshold functions
- linear combination
- feature vectors
- sparse coding
- real valued
- phase transition
- high dimensional
- uniform distribution
- high levels
- training set
- weight vector
- feature space
- objective function
- agnostic learning
- neural network