One-pass Stochastic Gradient Descent in Overparametrized Two-layer Neural Networks.
Jiaming XuHanjing ZhuPublished in: CoRR (2021)
Keyphrases
- stochastic gradient descent
- neural network
- loss function
- least squares
- matrix factorization
- step size
- random forests
- regularization parameter
- support vector machine
- weight vector
- multiple kernel learning
- online algorithms
- genetic algorithm
- importance sampling
- random forest
- collaborative filtering
- logistic regression
- decision trees
- back propagation
- benchmark datasets
- semi supervised
- pairwise
- training data