Convergence of Momentum-Based Stochastic Gradient Descent.
Ruinan JinXingkang HePublished in: ICCA (2020)
Keyphrases
- stochastic gradient descent
- step size
- convergence rate
- learning rate
- least squares
- matrix factorization
- loss function
- convergence speed
- weight vector
- random forests
- importance sampling
- support vector machine
- pairwise
- regularization parameter
- multiple kernel learning
- online algorithms
- cost function
- machine learning
- negative matrix factorization
- iterative algorithms