-
A novel adaptive learning rate scheduler for deep neural networks
Optimizing deep neural networks is largely thought to be an empirical pr...
read it
-
Deep Q-Networks for Accelerating the Training of Deep Neural Networks
In this paper, we propose a principled deep reinforcement learning (RL) ...
read it
-
EOS: Automatic In-vivo Evolution of Kernel Policies for Better Performance
Today's monolithic kernels often implement a small, fixed set of policie...
read it
-
Tune smarter not harder: A principled approach to tuning learning rates for shallow nets
Effective hyper-parameter tuning is essential to guarantee the performan...
read it
-
AutoLR: An Evolutionary Approach to Learning Rate Policies
The choice of a proper learning rate is paramount for good Artificial Ne...
read it
-
A Dynamic Sampling Adaptive-SGD Method for Machine Learning
We propose a stochastic optimization method for minimizing loss function...
read it
-
Dynamic learning rate using Mutual Information
This paper demonstrates dynamic hyper-parameter setting, for deep neural...
read it
Demystifying Learning Rate Polices for High Accuracy Training of Deep Neural Networks
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.
READ FULL TEXT
Comments
There are no comments yet.