AdaS: Adaptive Scheduling of Stochastic Gradients
arXiv:2006.06587
Abstract
The choice of step-size used in Stochastic Gradient Descent (SGD) optimization is empirically selected in most training procedures. Moreover, the use of scheduled learning techniques such as Step-Decaying, Cyclical-Learning, and Warmup to tune the step-size requires extensive practical experience--offering limited insight into how the parameters update--and is not consistent across applications. This work attempts to answer a question of interest to both researchers and practitioners, namely \textit{"how much knowledge is gained in iterative training of deep neural networks?"} Answering this question introduces two useful metrics derived from the singular values of the low-rank factorization of convolution layers in deep neural networks. We introduce the notions of \textit{"knowledge gain"} and \textit{"mapping condition"} and propose a new algorithm called Adaptive Scheduling (AdaS) that utilizes these derived metrics to adapt the SGD learning rate proportionally to the rate of change in knowledge gain over successive iterations. Experimentation reveals that, using the derived metrics, AdaS exhibits: (a) faster convergence and superior generalization over existing adaptive learning methods; and (b) lack of dependence on a validation set to determine when to stop training. Code is available at \url{https://github.com/mahdihosseini/AdaS}.
arXiv commentCode is available at https://github.com/mahdihosseini/AdaS
References in corpus (9)
- Adam: A Method for Stochastic Optimization
- ADADELTA: An Adaptive Learning Rate Method
- SGDR: Stochastic Gradient Descent with Warm Restarts
- On the Convergence of Adam and Beyond
- The Marginal Value of Adaptive Gradient Methods in Machine Learning
- No More Pesky Learning Rates
- Practical recommendations for gradient-based training of deep architectures
- Online Learning Rate Adaptation with Hypergradient Descent
- Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates