An interference-robust stochastic gradient algorithm with a gradient-adaptive step-size.
Akihiko SugiyamaPublished in: ICASSP (3) (1993)
Keyphrases
- stochastic gradient
- step size
- variable step size
- steepest descent method
- stochastic gradient descent
- cost function
- convergence rate
- gradient method
- least mean square
- learning algorithm
- optimization algorithm
- convergence speed
- simulated annealing
- computational complexity
- image quality
- nearest neighbor classifier
- optimal solution
- monte carlo
- neural network