We explore the usage of the Levenberg-Marquardt (LM) algorithm for regression (non-linear least squares) and classification (generalized Gauss-Newton methods) tasks in neural networks. We compare the performance of the LM method with other popular first-order algorithms such as SGD and Adam, as well as other second-order algorithms such as L-BFGS , Hessian-Free and KFAC. We further speed up the LM method by using adaptive momentum, learning rate line search, and uphill step acceptance.
翻译:我们探索在神经网络中使用Levenberg-Marquardt(LM)算法来进行回归(非线性最低方)和分类(通用高斯-牛顿方法)任务。我们将LM方法的性能与SGD和Adam等其他受欢迎的一级算法以及L-BFGS、Hessian-free和KFAC等其他二级算法进行比较。我们利用适应性动力、学习率线搜索和上坡步接受等方法,进一步加快LM方法的速度。