Training Quantized Neural Networks to Global Optimality via Semidefinite Programming.
Burak BartanMert PilanciPublished in: CoRR (2021)
Keyphrases
- semidefinite programming
- semidefinite
- global optimality
- neural network
- training process
- linear programming
- globally optimal
- convex programming
- primal dual
- interior point methods
- kernel matrix
- training examples
- global optimization
- optimal solution
- training set
- maximum margin
- learning algorithm
- training data
- linear program
- supervised learning
- convex relaxation
- training samples
- convex optimization
- nonlinear programming
- optimality conditions
- model selection