Convex Relaxations of ReLU Neural Networks Approximate Global Optima in Polynomial Time.
Sungyoon KimMert PilanciPublished in: CoRR (2024)
Keyphrases
- global optima
- neural network
- convex relaxation
- global optimization
- optimization problems
- optimization algorithm
- global optimum
- multi label
- optimization methods
- global search
- convex optimization
- genetic algorithm
- function optimization
- globally optimal
- control parameters
- artificial neural networks
- multistage
- premature convergence
- multiple kernel learning
- metaheuristic
- estimation of distribution algorithms
- simulated annealing
- search algorithm
- learning algorithm
- computational complexity
- genetic algorithm ga
- multi objective
- model selection