Subspace Fitting Meets Regression: The Effects of Supervision and Orthonormality Constraints on Double Descent of Generalization Errors.
Yehuda DarPaul MayerLorenzo LuziRichard G. BaraniukPublished in: ICML (2020)
Keyphrases
- residual errors
- constraint satisfaction
- low dimensional
- indirect effects
- feature extraction
- least squares
- gaussian processes
- high dimensional
- artificial neural networks
- active learning
- neural network
- regression model
- support vector
- constraint programming
- face recognition
- feature space
- regression methods
- error analysis
- cross validation
- input data
- pairwise