- Abstract: Hyperparameter tuning is one of the most time-consuming workloads in deep learning. State-of-the-art optimizers, such as AdaGrad, RMSProp and Adam, reduce this labor by adaptively tuning an individual learning rate for each variable. Recently researchers have shown renewed interest in simpler methods like momentum SGD as they may yield better results. Motivated by this trend, we ask: can simple adaptive methods, based on SGD perform as well or better? We revisit the momentum SGD algorithm and show that hand-tuning a single learning rate and momentum makes it competitive with Adam. We then analyze its robustness to learning rate misspecification and objective curvature variation. Based on these insights, we design YellowFin, an automatic tuner for momentum and learning rate in SGD. YellowFin optionally uses a negative-feedback loop to compensate for the momentum dynamics in asynchronous settings on the fly. We empirically show YellowFin can converge in fewer iterations than Adam on ResNets and LSTMs for image recognition, language modeling and constituency parsing, with a speedup of up to $3.28$x in synchronous and up to $2.69$x in asynchronous settings.
- TL;DR: YellowFin is an SGD based optimizer with both momentum and learning rate adaptivity.
- Keywords: adaptive optimizer, momentum, hyperparameter tuning