Disentangling the Predictive Variance of Deep Ensembles through the Neural Tangent Kernel.
Seijin KobayashiPau Vilimelis AceitunoJohannes von OswaldPublished in: CoRR (2022)
Keyphrases
- network architecture
- kernel methods
- neural network
- kernel function
- feature space
- ensemble methods
- bio inspired
- support vector
- kernel regression
- correlation coefficient
- graph kernels
- machine learning
- convolution kernel
- ensemble selection
- decision stumps
- kernel matrix
- base classifiers
- standard deviation
- covariance matrix
- decision trees
- random forests
- kernel machines
- similarity function
- spike trains
- sample size
- tangent distance
- word sense induction