arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.03804cs.LGstat.ML
收藏

精确随机二阶深度学习

Exact Stochastic Second Order Deep Learning

Directed Energy Research Centre(定向能研究中心);Technology Innovation Institute(技术创新研究院)

Fares B. Mehouachi, Chaouki Kasmi

摘要:

深度学习中的优化主要由围绕反向传播的中心概念构建的一阶方法主导。考虑二阶导数的二阶优化方法尽管具有优越的理论性质,但使用得很少。二阶方法的这种不足源于其过高的计算成本、糟糕的性能以及深度学习不可避免的非凸性。为了解决二阶优化的不足,人们进行了几次尝试,但没有得到一个具有成本效益的解决方案,更不用说精确的解决方案了。在这项工作中,我们证明了深度学习中这个长期存在的问题可以在随机情况下得到解决,只要神经网络得到适当的正则化。有趣的是,我们提供了一个表达式的随机海森和它的确切特征值。我们提供了一个封闭形式的公式,精确的随机二阶牛顿方向,我们解决了非凸性问题,并调整我们的精确解,有利于平坦的最小值,通过正则化和谱调整。我们在流行的数据集上测试了我们的精确随机二阶方法,并揭示了它对深度学习的充分性。

英文摘要:

Optimization in Deep Learning is mainly dominated by first-order methods which are built around the central concept of backpropagation. Second-order optimization methods, which take into account the second-order derivatives are far less used despite superior theoretical properties. This inadequacy of second-order methods stems from its exorbitant computational cost, poor performance, and the ineluctable non-convex nature of Deep Learning. Several attempts were made to resolve the inadequacy of second-order optimization without reaching a cost-effective solution, much less an exact solution. In this work, we show that this long-standing problem in Deep Learning could be solved in the stochastic case, given a suitable regularization of the neural network. Interestingly, we provide an expression of the stochastic Hessian and its exact eigenvalues. We provide a closed-form formula for the exact stochastic second-order Newton direction, we solve the non-convexity issue and adjust our exact solution to favor flat minima through regularization and spectral adjustment. We test our exact stochastic second-order method on popular datasets and reveal its adequacy for Deep Learning.

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。

↑