Automatic and Simultaneous Adjustment of Learning Rate and Momentum for Stochastic Gradient Descent.
Tomer LancewickiSelçuk KöprüPublished in: CoRR (2019)
Keyphrases
- learning rate
- stochastic gradient descent
- weight vector
- training speed
- convergence rate
- step size
- learning algorithm
- convergence speed
- least squares
- matrix factorization
- loss function
- training algorithm
- random forests
- differential evolution
- missing data
- machine learning algorithms
- particle swarm optimization
- delta bar delta