Non-linear, Sparse Dimensionality Reduction via Path Lasso Penalized Autoencoders.
Oskar AllerboRebecka JörnstenPublished in: J. Mach. Learn. Res. (2021)
Keyphrases
- dimensionality reduction
- sparse representation
- high dimensional
- variable selection
- random projections
- high dimensional data
- group lasso
- least squares
- feature selection
- kernel trick
- regularized regression
- high dimension
- low dimensional
- elastic net
- high dimensionality
- denoising
- sparse coding
- manifold learning
- compressive sensing
- sparse data
- principal component analysis
- compressed sensing
- dimensionality reduction methods
- data representation
- shortest path
- pattern recognition
- basis pursuit
- linear regression
- feature space
- dimension reduction
- model selection
- piece wise linear
- generalized linear models
- optimal path
- data points
- structure preserving
- input space
- pattern recognition and machine learning
- feature extraction
- machine learning
- singular value decomposition
- maximum likelihood
- fisher discriminant analysis
- unsupervised learning
- nearest neighbor
- image processing
- face recognition
- kernel learning
- regression model
- multiple kernel learning
- sample size
- metric learning
- path planning
- linear discriminant analysis