DeepAI AI Chat
Log In Sign Up

Coupling Adaptive Batch Sizes with Learning Rates

by   Lukas Balles, et al.

Mini-batch stochastic gradient descent and variants thereof have become standard for large-scale empirical risk minimization like the training of neural networks. These methods are usually used with a constant batch size chosen by simple empirical inspection. The batch size significantly influences the behavior of the stochastic optimization algorithm, though, since it determines the variance of the gradient estimates. This variance also changes over the optimization process; when using a constant batch size, stability and convergence is thus often enforced by means of a (manually tuned) decreasing learning rate schedule. We propose a practical method for dynamic batch size adaptation. It estimates the variance of the stochastic gradients and adapts the batch size to decrease the variance proportionally to the value of the objective function, removing the need for the aforementioned learning rate decrease. In contrast to recent related work, our algorithm couples the batch size to the learning rate, directly reflecting the known relationship between the two. On popular image classification benchmarks, our batch size adaptation yields faster optimization convergence, while simultaneously simplifying learning rate tuning. A TensorFlow implementation is available.


page 1

page 2

page 3

page 4


Stochastic gradient descent with random learning rate

We propose to optimize neural networks with a uniformly-distributed rand...

Variance Regularization for Accelerating Stochastic Optimization

While nowadays most gradient-based optimization methods focus on explori...

Batch size-invariance for policy optimization

We say an algorithm is batch size-invariant if changes to the batch size...

Automated Learning Rate Scheduler for Large-batch Training

Large-batch training has been essential in leveraging large-scale datase...

Hyper-Learning for Gradient-Based Batch Size Adaptation

Scheduling the batch size to increase is an effective strategy to contro...

Model Accuracy and Runtime Tradeoff in Distributed Deep Learning:A Systematic Study

This paper presents Rudra, a parameter server based distributed computin...

Dynamic Batch Adaptation

Current deep learning adaptive optimizer methods adjust the step magnitu...