Gradient-only line searches to automatically determine learning rates for a variety of stochastic training algorithms
This addresses the need to tune sensitive learning rate hyperparameters in neural network training, though it is incremental as it builds on existing line search methods.
The paper tackles the problem of automatically determining learning rates in stochastic neural network training by applying the Gradient-Only Line Search that is Inexact (GOLS-I) to various algorithms, architectures, and datasets, finding it competitive with manually tuned rates and effective over 15 orders of magnitude for most algorithms.
Gradient-only and probabilistic line searches have recently reintroduced the ability to adaptively determine learning rates in dynamic mini-batch sub-sampled neural network training. However, stochastic line searches are still in their infancy and thus call for an ongoing investigation. We study the application of the Gradient-Only Line Search that is Inexact (GOLS-I) to automatically determine the learning rate schedule for a selection of popular neural network training algorithms, including NAG, Adagrad, Adadelta, Adam and LBFGS, with numerous shallow, deep and convolutional neural network architectures trained on different datasets with various loss functions. We find that GOLS-I's learning rate schedules are competitive with manually tuned learning rates, over seven optimization algorithms, three types of neural network architecture, 23 datasets and two loss functions. We demonstrate that algorithms, which include dominant momentum characteristics, are not well suited to be used with GOLS-I. However, we find GOLS-I to be effective in automatically determining learning rate schedules over 15 orders of magnitude, for most popular neural network training algorithms, effectively removing the need to tune the sensitive hyperparameters of learning rate schedules in neural network training.