Stochastic Gradient Descent with Exponential Convergence Rates of Expected Classification Errors.
Atsushi NitandaTaiji SuzukiPublished in: AISTATS (2019)
Keyphrases
- convergence rate
- stochastic gradient descent
- step size
- classification error
- convergence speed
- learning rate
- training set
- training samples
- class labels
- matrix factorization
- loss function
- least squares
- generalization error
- hyperparameters
- sample size
- base classifiers
- random forests
- regularization parameter
- face recognition