arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.00720math.OC
收藏

绝对误差界下不精确预言机加速方法的非渐近分析

Nonasymptotic Analysis of Accelerated Methods With Inexact Oracle Under Absolute Error Bound

Beijing International Center for Mathematical Research, Peking University(北京大学北京国际数学研究中心);The Ohio State University(俄亥俄州立大学)

Yin Liu, Sam Davanloo Tajbakhsh

AI总结:

研究具有不精确梯度预言机的加速方法用于解决确定性光滑凸问题,用PEP分析收敛界,得出GOGM和GFGM新收敛界,分析权衡与最优策略,建立累积误差下界并开发满足下界的PEP解。

摘要:

由于在各种新兴应用中获取精确梯度是不可能或计算成本高昂的,具有不精确预言机的一阶算法的性能分析最近受到关注。先前研究表明加速一阶方法的性能比非加速方法对梯度误差更敏感。本文研究了两种具有不精确梯度的加速方法用于解决确定性光滑凸问题的非渐近收敛界。使用性能估计问题(PEP)作为主要工具分析基础算法的收敛界。通过找到PEP的解析解,我们得出了具有不精确梯度预言机的广义优化梯度法(GOGM)和广义快速梯度法(GFGM)遵循绝对误差界的新收敛界。接着分析了收敛界中消失项和累积误差之间的权衡以指导找到最优步长。此外,确定了沿迭代设置梯度不精确性的最优策略,确保累积误差从属于消失项。最后,为满足两个属性的一类一阶方法建立了累积误差的下界,这促使我们为GOGM和GFGM方法开发满足此下界的PEP解。

英文摘要:

Performance analysis of first-order algorithms with inexact oracles has gained recent attention due to various emerging applications in which obtaining exact gradients is impossible or computationally expensive. Previous research has demonstrated that the performance of accelerated first-order methods is more sensitive to gradient errors compared with non-accelerated ones. This paper investigates the nonasymptotic convergence bound of two accelerated methods with inexact gradients to solve deterministic smooth convex problems. Performance Estimation Problem (PEP) is used as the primary tool to analyze the convergence bounds of the underlying algorithms. By finding an analytical solution to PEP, we derive novel convergence bounds of the Generalized Optimized Gradient Method (GOGM) and Generalized Fast Gradient Method (GFGM) with inexact gradient oracles following the absolute error bound. Next, we analyze the tradeoff between the vanishing term and the accumulated error in the convergence bound that guides finding the optimal stepsize. Furthermore, we determine the optimal strategy to set the gradient inexactness along iterations, ensuring that the accumulated error remains subordinate to the vanishing term. Finally, we establish a lower bound for accumulated error for a subclass of first-order methods satisfying two properties, which then motivated us to develop PEP solutions satisfying this lower bound for GOGM and GFGM methods.

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。

↑