Timezone: »

 
Poster
Using Statistics to Automate Stochastic Optimization
Hunter Lang · Lin Xiao · Pengchuan Zhang

Thu Dec 12 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #173
in Deep Learning -- Optimization for Deep Networks »

Despite the development of numerous adaptive optimizers, tuning the learning rate of stochastic gradient methods remains a major roadblock to obtaining good practical performance in machine learning. Rather than changing the learning rate at each iteration, we propose an approach that automates the most common hand-tuning heuristic: use a constant learning rate until "progress stops," then drop. We design an explicit statistical test that determines when the dynamics of stochastic gradient descent reach a stationary distribution. This test can be performed easily during training, and when it fires, we decrease the learning rate by a constant multiplicative factor. Our experiments on several deep learning tasks demonstrate that this statistical adaptive stochastic approximation (SASA) method can automatically find good learning rate schedules and match the performance of hand-tuned methods using default settings of its parameters. The statistical testing helps to control the variance of this procedure and improves its robustness.

Keywords: Optimization for Deep Networks · Deep Learning · Stochastic Optimization · Algorithms -> Stochastic Methods; Optimization
[ Paper]  [ Poster] 

Author Information

Hunter Lang (Microsoft Research)
Lin Xiao (Microsoft Research)
Pengchuan Zhang (Microsoft Research)

More from the Same Authors