arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1606.01467cs.LGcs.NE
收藏

用于加速深度神经网络训练的深度Q网络

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

Jie Fu

摘要:

在本文中,我们提出了一种原则性的深度强化学习(RL)方法,该方法能够加快一般深度神经网络(DNN)的收敛速度。通过我们的方法,深度RL代理(本工作中优化器的同义词)用于自动学习有关如何在DNN优化期间调度学习率的策略。在训练过程中,智能体的状态特征从被优化者的权重统计中学习。该代理的奖励函数被设计为学习策略,以最小化给定特定性能目标的优化者的训练时间。代理的动作对应于在训练期间改变被优化者的学习率。据我们所知,这是首次尝试使用深度RL来学习如何优化大型DNN。我们在标准基准数据集上进行了大量的实验,并证明了我们的方法学习的政策的有效性。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑