Tune without Validation: Searching for Learning Rate and Weight Decay on Training Sets.
Lorenzo BrigatoStavroula G. MougiakakouPublished in: CoRR (2024)
Keyphrases
- learning rate
- training set
- learning algorithm
- convergence rate
- error function
- hidden layer
- convergence speed
- multilayer neural networks
- adaptive learning rate
- training examples
- rapid convergence
- active learning
- convergence theorem
- weight vector
- activation function
- delta bar delta
- training samples
- supervised learning
- genetic programming
- training algorithm
- classification accuracy
- search space
- search capabilities
- support vector
- reinforcement learning
- decision trees
- genetic algorithm
- neural network