When can we Approximate Wide Contrastive Models with Neural Tangent Kernels and Principal Component Analysis?
Gautham Govind AnilPascal Mattia EsserDebarghya GhoshdastidarPublished in: CoRR (2024)
Keyphrases
- principal component analysis
- wide range
- statistical models
- neural network
- feature space
- probabilistic model
- dimensionality reduction
- covariance matrix
- neural models
- independent component analysis
- tangent distance
- neural classifier
- learning rules
- parametric models
- linear model
- principal components
- singular value decomposition
- linear combination
- feature extraction