Franceschi, L; Donini, M; Frasconi, P; Pontil, M; (2017) Forward and Reverse Gradient-Based Hyperparameter Optimization. In: Precup, D and Teh, YW, (eds.) Proceedings of the 34th International Conference on Machine Learning 2017. (pp. pp. 1165-1173). JMLR: Sydney, Australia.

Preview

Text Franceschi_Forward_Reverse_Gradient-Based.pdf - Published Version Download (414kB) | Preview

Abstract

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.

Download activity - last month

Export as XMLCSVJSON

Download activity - last 12 months

Export as CSVXMLJSON

Downloads by country - last 12 months

Export as CSVXMLJSON

Archive Staff Only

View Item