qan
Deep Q-Networks for Accelerating the Training of Deep Neural Networks
view repo
In this paper, we propose a principled deep reinforcement learning (RL) approach that is able to accelerate the convergence rate of general deep neural networks (DNNs). With our approach, a deep RL agent (synonym for optimizer in this work) is used to automatically learn policies about how to schedule learning rates during the optimization of a DNN. The state features of the agent are learned from the weight statistics of the optimizee during training. The reward function of this agent is designed to learn policies that minimize the optimizee's training time given a certain performance goal. The actions of the agent correspond to changing the learning rate for the optimizee during training. As far as we know, this is the first attempt to use deep RL to learn how to optimize a large-sized DNN. We perform extensive experiments on a standard benchmark dataset and demonstrate the effectiveness of the policies learned by our approach.
READ FULL TEXT
Learning Rate (LR) is an important hyper-parameter to tune for effective...
read it
The potential of Reinforcement Learning (RL) has been demonstrated throu...
read it
While Deep Neural Networks (DNNs) are becoming the state-of-the-art for ...
read it
Deep Reinforcement Learning (DRL) has become a powerful strategy to solv...
read it
Reinforcement learning (RL) algorithms have made huge progress in recent...
read it
The success of deep learning in the computer vision and natural language...
read it
Deep Reinforcement Learning (DeepRL) models surpass human-level performa...
read it
Deep Q-Networks for Accelerating the Training of Deep Neural Networks
Comments
There are no comments yet.