DeepAI AI Chat
Log In Sign Up

WNGrad: Learn the Learning Rate in Gradient Descent

by   Xiaoxia Wu, et al.

Adjusting the learning rate schedule in stochastic gradient methods is an important unresolved problem which requires tuning in practice. If certain parameters of the loss function such as smoothness or strong convexity constants are known, theoretical learning rate schedules can be applied. However, in practice, such parameters are not known, and the loss function of interest is not convex in any case. The recently proposed batch normalization reparametrization is widely adopted in most neural network architectures today because, among other advantages, it is robust to the choice of Lipschitz constant of the gradient in loss function, allowing one to set a large learning rate without worry. Inspired by batch normalization, we propose a general nonlinear update rule for the learning rate in batch and stochastic gradient descent so that the learning rate can be initialized at a high value, and is subsequently decreased according to gradient observations along the way. The proposed method is shown to achieve robustness to the relationship between the learning rate and the Lipschitz constant, and near-optimal convergence rates in both the batch and stochastic settings (O(1/T) for smooth loss in the batch setting, and O(1/√(T)) for convex loss in the stochastic setting). We also show through numerical evidence that such robustness of the proposed method extends to highly nonconvex and possibly non-smooth loss function in deep learning problems.Our analysis establishes some first theoretical understanding into the observed robustness for batch normalization and weight normalization.


page 1

page 2

page 3

page 4


Theoretical Analysis of Auto Rate-Tuning by Batch Normalization

Batch Normalization (BN) has become a cornerstone of deep learning acros...

AdaGrad stepsizes: Sharp convergence over nonconvex landscapes, from any initialization

Adaptive gradient methods such as AdaGrad and its variants update the st...

Training trajectories, mini-batch losses and the curious role of the learning rate

Stochastic gradient descent plays a fundamental role in nearly all appli...

Robust Learning via Persistency of Excitation

Improving adversarial robustness of neural networks remains a major chal...

On the Outsized Importance of Learning Rates in Local Update Methods

We study a family of algorithms, which we refer to as local update metho...

Automatic, Dynamic, and Nearly Optimal Learning Rate Specification by Local Quadratic Approximation

In deep learning tasks, the learning rate determines the update step siz...

On the Convergence and Robustness of Batch Normalization

Despite its empirical success, the theoretical underpinnings of the stab...