UnderGrad: A Universal Black-Box Optimization Method with Almost Dimension-Free Convergence Rate Guarantees.
Kimon AntonakopoulosDong Quan VuVolkan CevherKfir Y. LevyPanayotis MertikopoulosPublished in: ICML (2022)
Keyphrases
- black box
- optimization method
- convergence rate
- convergence speed
- optimization algorithm
- optimization methods
- differential evolution
- learning rate
- black boxes
- optimization procedure
- step size
- evolutionary algorithm
- white box
- optimization process
- genetic algorithm
- nonlinear optimization
- particle swarm
- nelder mead simplex
- global optimum
- mutation operator
- simulated annealing
- metaheuristic
- global convergence
- gradient method
- white box testing
- search algorithm
- test cases
- cost function
- multi objective
- premature convergence
- error rate
- learning algorithm
- number of iterations required
- neural network