Learning the Step-size Policy for the Limited-Memory Broyden-Fletcher-Goldfarb-Shanno Algorithm.
Lucas N. EgidioAnders HanssonBo WahlbergPublished in: CoRR (2020)
Keyphrases
- learning algorithm
- step size
- cost function
- convergence rate
- memory space
- stochastic gradient descent
- limited memory
- optimal solution
- variable step size
- dynamic programming
- objective function
- np hard
- search space
- particle swarm optimization
- optimization algorithm
- high accuracy
- probability distribution
- evolutionary algorithm
- steepest descent method
- computational complexity