Demystifying Learning Rate Polices for High Accuracy Training of Deep Neural Networks

by   Yanzhao Wu, et al.

Learning Rate (LR) is an important hyper-parameter to tune for effective training of deep neural networks (DNNs). Even for the baseline of a constant learning rate, it is non-trivial to choose a good constant value for training a DNN. Dynamic learning rates involve multi-step tuning of LR values at various stages of the training process and offer high accuracy and fast convergence. However, they are much harder to tune. In this paper, we present a comprehensive study of 13 learning rate functions and their associated LR policies by examining their range parameters, step parameters, and value update parameters. We propose a set of metrics for evaluating and selecting LR policies, including the classification confidence, variance, cost, and robustness, and implement them in LRBench, an LR benchmarking system. LRBench can assist end-users and DNN developers to select good LR policies and avoid bad LR policies for training their DNNs. We tested LRBench on Caffe, an open source deep learning framework, to showcase the tuning optimization of LR policies. Evaluated through extensive experiments, we attempt to demystify the tuning of LR policies by identifying good LR policies with effective LR value ranges and step sizes for LR update schedules.



page 1

page 2

page 3

page 4


A novel adaptive learning rate scheduler for deep neural networks

Optimizing deep neural networks is largely thought to be an empirical pr...

Deep Q-Networks for Accelerating the Training of Deep Neural Networks

In this paper, we propose a principled deep reinforcement learning (RL) ...

EOS: Automatic In-vivo Evolution of Kernel Policies for Better Performance

Today's monolithic kernels often implement a small, fixed set of policie...

Tune smarter not harder: A principled approach to tuning learning rates for shallow nets

Effective hyper-parameter tuning is essential to guarantee the performan...

Evolving Learning Rate Optimizers for Deep Neural Networks

Artificial Neural Networks (ANNs) became popular due to their successful...

Training With Data Dependent Dynamic Learning Rates

Recently many first and second order variants of SGD have been proposed ...

Sanity Checks for Lottery Tickets: Does Your Winning Ticket Really Win the Jackpot?

There have been long-standing controversies and inconsistencies over the...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.