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 2002.12642cs.LGstat.ML
收藏

深度学习应用中的优化方法重要吗?

Do optimization methods in deep learning applications matter?

Cukurova University(丘库罗瓦大学);Lawrence Berkeley National Laboratory(劳伦斯伯克利国家实验室);Energy Sciences Network(能源科学网络)

Buse Melis Ozyildirim, Mariam Kiran

摘要:

随着深度学习的发展、指数数据增长和模型复杂性的增加,开发高效的优化方法吸引了大量的研究关注。一些实现倾向于使用共轭梯度(CG)和随机梯度下降(SGD)作为实现快速收敛的实用且优雅的解决方案,然而,这些优化过程也在跨深度学习应用的学习中存在许多限制。最近的研究正在探索高阶优化函数作为更好的方法,但这些方法在实际应用中存在非常复杂的计算挑战。在本文中,我们的实验表明,Levemberg-Marquardt(LM)显着取代最优收敛,但遭受非常大的处理时间,增加了训练的复杂性,分类和强化学习问题。我们的实验在标准CIFAR、MNIST、CartPole和FlappyBird实验中比较了现成的优化函数(CG、SGD、LM和L-BFGS)。本文提出了关于使用哪些优化函数以及哪些函数将受益于并行化工作以提高预训练时间和学习率收敛的论点。

英文摘要:

With advances in deep learning, exponential data growth and increasing model complexity, developing efficient optimization methods are attracting much research attention. Several implementations favor the use of Conjugate Gradient (CG) and Stochastic Gradient Descent (SGD) as being practical and elegant solutions to achieve quick convergence, however, these optimization processes also present many limitations in learning across deep learning applications. Recent research is exploring higher-order optimization functions as better approaches, but these present very complex computational challenges for practical use. Comparing first and higher-order optimization functions, in this paper, our experiments reveal that Levemberg-Marquardt (LM) significantly supersedes optimal convergence but suffers from very large processing time increasing the training complexity of both, classification and reinforcement learning problems. Our experiments compare off-the-shelf optimization functions(CG, SGD, LM and L-BFGS) in standard CIFAR, MNIST, CartPole and FlappyBird experiments.The paper presents arguments on which optimization functions to use and further, which functions would benefit from parallelization efforts to improve pretraining time and learning rate convergence.

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。

↑