Asynchronous stochastic gradient descent for DNN training.
Shanshan ZhangCe ZhangZhao YouRong ZhengBo XuPublished in: ICASSP (2013)
Keyphrases
- stochastic gradient descent
- least squares
- early stopping
- loss function
- step size
- matrix factorization
- training process
- support vector machine
- random forests
- multiple kernel learning
- weight vector
- regularization parameter
- importance sampling
- online algorithms
- small number
- upper bound
- learning algorithm
- linear svm
- training data
- feature extraction