arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1409.2045math.OCcs.LGstat.ML
收藏

在线有限记忆BFGS的整体收敛

Global Convergence of Online Limited Memory BFGS

University of Pennsylvania(宾夕法尼亚大学)

Aryan Mokhtari, Alejandro Ribeiro

摘要:

建立了求解大规模机器学习中随机目标最优化问题的Broyden-Fletcher- Goldfarb-Shanno(BFGS)拟牛顿法的在线(随机)有限记忆版本的整体收敛.样本函数的Hessian特征值的上界足以保证曲率近似矩阵具有有界的行列式和迹线,这反过来又允许以概率1收敛到最优参数。支持向量机与合成数据的数值实验展示减少收敛时间相对于随机梯度下降算法,以及减少存储和计算相对于其他在线拟牛顿法。通过对搜索引擎广告问题的实验评估,证实了这些优点在实际应用中也得到了体现。

英文摘要:

Global convergence of an online (stochastic) limited memory version of the Broyden-Fletcher- Goldfarb-Shanno (BFGS) quasi-Newton method for solving optimization problems with stochastic objectives that arise in large scale machine learning is established. Lower and upper bounds on the Hessian eigenvalues of the sample functions are shown to suffice to guarantee that the curvature approximation matrices have bounded determinants and traces, which, in turn, permits establishing convergence to optimal arguments with probability 1. Numerical experiments on support vector machines with synthetic data showcase reductions in convergence time relative to stochastic gradient descent algorithms as well as reductions in storage and computation relative to other online quasi-Newton methods. Experimental evaluation on a search engine advertising problem corroborates that these advantages also manifest in practical applications.

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。

↑