Log In Sign Up

Understanding and Detecting Convergence for Stochastic Gradient Descent with Momentum

by   Jerry Chee, et al.

Convergence detection of iterative stochastic optimization methods is of great practical interest. This paper considers stochastic gradient descent (SGD) with a constant learning rate and momentum. We show that there exists a transient phase in which iterates move towards a region of interest, and a stationary phase in which iterates remain bounded in that region around a minimum point. We construct a statistical diagnostic test for convergence to the stationary phase using the inner product between successive gradients and demonstrate that the proposed diagnostic works well. We theoretically and empirically characterize how momentum can affect the test statistic of the diagnostic, and how the test statistic captures a relatively sparse signal within the gradients in convergence. Finally, we demonstrate an application to automatically tune the learning rate by reducing it each time stationarity is detected, and show the procedure is robust to mis-specified initial rates.


Convergence diagnostics for stochastic gradient descent with constant step size

Iterative procedures in stochastic optimization are typically comprised ...

Robust Learning Rate Selection for Stochastic Optimization via Splitting Diagnostic

This paper proposes SplitSGD, a new stochastic optimization algorithm wi...

On Convergence-Diagnostic based Step Sizes for Stochastic Gradient Descent

Constant step-size Stochastic Gradient Descent exhibits two phases: a tr...

Understanding the Role of Momentum in Stochastic Gradient Methods

The use of momentum in stochastic gradient methods has become a widespre...

Adaptive learning rates and parallelization for stochastic, sparse, non-smooth gradients

Recent work has established an empirically successful framework for adap...

On the equivalence of different adaptive batch size selection strategies for stochastic gradient descent methods

In this study, we demonstrate that the norm test and inner product/ortho...

Convergence of online k-means

We prove asymptotic convergence for a general class of k-means algorithm...