arXiv (Cornell University) · 2012 · 291 citations · 17 references
ComputingComputer ScienceMachine LearningOptimizationStatistical LearningAdaptive LearningConvex OptimizationGradient-based OptimizationOptimization For Machine LearningReinforcement LearningStochastic OptimizationAdaptive OptimizationExpected Prediction ErrorGradient DescentStochastic Gradient DescentTuning
The performance of stochastic gradient descent (SGD) depends critically on how learning rates are tuned and decreased over time. We propose a method to automatically adjust multiple learning rates so as to minimize the expected error at any one time. The method relies on local gradient variations across samples. In our approach, learning rates can increase as well as decrease, making it suitable for non-stationary problems. Using a number of convex and non-convex learning tasks, we show that the resulting algorithm matches the performance of SGD or other adaptive approaches with their best settings obtained through systematic search, and effectively removes the need for learning rate tuning.
17
A Stochastic Approximation Method
Herbert Robbins, Sutton Monro · The Annals of Mathematical Statistics · 1951 · 9.6K citations · Full text
Yann LeCun, Léon Bottou, Genevieve Orr et al. · Neural Information Processing Systems · 1998 · 1.4K citations