ENOT: Expectile Regularization for Fast and Accurate Training of Neural Optimal Transport.
Nazar BuzunMaksim BobrinDmitry V. DylovPublished in: CoRR (2024)
Keyphrases
- early stopping
- high accuracy
- computationally efficient
- neural network
- dynamic programming
- training set
- worst case
- test set
- optimal control
- training process
- training algorithm
- optimal solution
- high quality
- support vector machine
- image processing
- learning algorithm
- training samples
- highly accurate
- network architecture
- machine learning