Convergence and convergence rate of stochastic gradient search in the case of multiple and non-isolated extrema.
Vladislav B. TadicPublished in: CDC (2010)
Keyphrases
- convergence rate
- stochastic gradient
- step size
- convergence speed
- learning rate
- global convergence
- stochastic gradient descent
- utility maximization
- gradient method
- gauss seidel method
- variable step size
- high dimensional
- image processing
- k means
- nearest neighbor classifier
- support vector
- multiscale
- faster convergence rate
- learning algorithm
- genetic algorithm