Forward and Reverse Gradient-Based Hyperparameter Optimization
This work addresses hyperparameter optimization for machine learning practitioners, offering incremental improvements in efficiency and scalability over existing methods.
The paper tackles the problem of efficiently computing gradients for hyperparameter optimization in iterative learning algorithms by introducing reverse-mode and forward-mode procedures, achieving real-time updates and scalability to large datasets.
We study two procedures (reverse-mode and forward-mode) for computing the gradient of the validation error with respect to the hyperparameters of any iterative learning algorithm such as stochastic gradient descent. These procedures mirror two methods of computing gradients for recurrent neural networks and have different trade-offs in terms of running time and space requirements. Our formulation of the reverse-mode procedure is linked to previous work by Maclaurin et al. [2015] but does not require reversible dynamics. The forward-mode procedure is suitable for real-time hyperparameter updates, which may significantly speed up hyperparameter optimization on large datasets. We present experiments on data cleaning and on learning task interactions. We also present one large-scale experiment where the use of previous gradient-based methods would be prohibitive.