Implicit Bias in Leaky ReLU Networks Trained on High-Dimensional Data.
Spencer FreiGal VardiPeter L. BartlettNathan SrebroWei HuPublished in: CoRR (2022)
Keyphrases
- high dimensional data
- nearest neighbor
- dimensionality reduction
- data sets
- high dimensionality
- high dimensional
- low dimensional
- data analysis
- subspace clustering
- similarity search
- high dimensions
- dimension reduction
- nonlinear dimensionality reduction
- data points
- sparse representation
- clustering high dimensional data
- data distribution
- original data
- variable selection
- linear discriminant analysis
- high dimensional datasets
- manifold learning
- high dimensional spaces
- input space
- variable weighting
- text data
- gene expression data
- lower dimensional
- input data
- knn