Neural Velocity for hyperparameter tuning
This addresses the challenge of efficient hyperparameter tuning for machine learning practitioners, though it appears incremental as it builds on existing validation loss methods.
The paper tackled the problem of hyperparameter tuning in neural networks by introducing NeVe, a dynamic training approach that uses neural velocity to adjust learning rates and define stopping criteria, reducing the need for a held-out dataset.
Hyperparameter tuning, such as learning rate decay and defining a stopping criterion, often relies on monitoring the validation loss. This paper presents NeVe, a dynamic training approach that adjusts the learning rate and defines the stop criterion based on the novel notion of "neural velocity". The neural velocity measures the rate of change of each neuron's transfer function and is an indicator of model convergence: sampling neural velocity can be performed even by forwarding noise in the network, reducing the need for a held-out dataset. Our findings show the potential of neural velocity as a key metric for optimizing neural network training efficiently