Implicit regularization in Heavy-ball momentum accelerated stochastic gradient descent.
Avrajit GhoshHe LyuXitong ZhangRongrong WangPublished in: CoRR (2023)
Keyphrases
- stochastic gradient descent
- least squares
- loss function
- matrix factorization
- step size
- regularization parameter
- weight vector
- learning rate
- random forests
- early stopping
- support vector machine
- online algorithms
- multiple kernel learning
- convergence rate
- image restoration
- convergence speed
- importance sampling
- decision trees
- online learning
- collaborative filtering
- active learning
- support vector
- objective function