On the Approximation Lower Bound for Neural Nets with Random Weights.
Sho SonodaMing LiFeilong CaoChangqin HuangYu Guang WangPublished in: CoRR (2020)
Keyphrases
- neural nets
- lower bound
- upper bound
- feed forward
- polynomial approximation
- weight function
- back propagation
- neural network
- branch and bound algorithm
- artificial neural networks
- objective function
- branch and bound
- constant factor
- weighted sum
- learning tasks
- randomized algorithm
- linear programming relaxation
- integrality gap
- hidden layer
- counter propagation
- worst case
- approximation algorithms
- linear combination
- lower and upper bounds
- np hard
- prior knowledge
- text classification
- activation function
- nearest neighbor
- optimal solution
- e learning
- decision making